Your search found 67 records
1 de Vries, T. T.; Anwar, Arif A. 2015. Irrigation scheduling using complex machine scheduling. Journal of Irrigation and Drainage Engineering, 141(5):04014065-1-04014065-8. [doi: https://doi.org/10.1061/(ASCE)IR.1943-4774.0000824]
Irrigation systems ; Mathematical models ; Water allocation ; Water users ; Costs ; Machine learning
(Location: IWMI HQ Call no: e-copy only Record No: H046653)
(1.09 MB)
Irrigation schedules are used in many irrigation schemes that operate on a rotational or arranged-demand basis. Determining these schedules is a complex problem, especially when done by hand. Operations research tools such as single machine scheduling are already used to schedule irrigation turns in systems where only one single user can irrigate simultaneously. This paper shows how multimachine scheduling can be used to determine arranged-demand schedules for systems where two or more users can irrigate at the same time. Two models are presented, as follows: (1) the simple multimachine scheduling model that establishes a schedule for systems where all outlets/user discharges are identical, and (2) the complex multimachine scheduling model that determines the schedule when flows to individual outlet/users are not necessarily identical.
2 Jean, N.; Burke, M.; Xie, M.; Davis, W. M.; Lobell, D. B.; Ermon, S. 2016. Combining satellite imagery and machine learning to predict poverty. Science, 353(6301):790-794. [doi: https://doi.org/10.1126/science.aaf7894]
Poverty ; Satellite imagery ; Forecasting ; Living standards ; Household consumption ; Household expenditure ; Machine learning ; Neural networks ; Models ; Performance evaluation ; Economic aspects ; Assets / Nigeria / Tanzania / Uganda / Malawi / Rwanda
(Location: IWMI HQ Call no: e-copy only Record No: H047755)
(7.12 MB)
Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries—Nigeria, Tanzania, Uganda, Malawi, and Rwanda—we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.
3 Sahoo, M.; Kasot, A.; Dhar, A.; Kar, A. 2018. On predictability of groundwater level in shallow wells using satellite observations. Water Resources Management, 32(4):1225-1244. [doi: https://doi.org/10.1007/s11269-017-1865-5]
Groundwater table ; Water levels ; Forecasting ; Satellite observation ; Wells ; Water storage ; Hydrological factors ; Performance indexes ; Remote sensing ; Soil moisture ; Rain ; River basins ; Machine learning ; Models / India / Indo-Gangetic Basin
(Location: IWMI HQ Call no: e-copy only Record No: H048810)
(2.94 MB)
Management of groundwater resources needs continuous and efficient monitoring networks. Sparsity of in situ measurements both spatially and temporally creates hindrance in framing groundwater management policies. Remotely sensed data can be a possible alternative. GRACE satellites can trace groundwater changes globally. Moreover, gridded rainfall (RF) and soil moisture (SM) data can shed some light on the hydrologic system. The present study attempts to use GRACE, RF and SM data at a local scale to predict groundwater level. Ground referencing of satellite data were done by using three machine learning techniques- Support Vector Regression (SVR), Random Forest Method (RFM) and Gradient Boosting Mechanism (GBM). The performance of the developed methodology was tested on a part of the Indo-Gangetic basin. The analyses were carried out for nine GRACE pixels to identify relationship between individual well measurements and satellite-derived data. These nine pixels are classified on the basis of presence or absence of hydrological features. Pixels with the presence of perennial streams showed reasonably good results. However, pixels with wells located mostly near the stream gave relatively poorer predictions. These results help in identifying wells which can reasonably represent the regional shallow groundwater dynamics.
4 Akpoti, K.; Kabo-bah, A. T.; Zwart, Sander J. 2019. Agricultural land suitability analysis: state-of-the-art and outlooks for integration of climate change analysis. Agricultural Systems, 173:172-208. [doi: https://doi.org/10.1016/j.agsy.2019.02.013]
Agricultural land ; Sustainable agriculture ; Sustainable Development Goals ; Land suitability ; Land use ; Integration ; Climate change ; Machine learning ; Crop production ; Crop yield ; Crop modelling ; Food security ; Environmental impact ; Planning ; Water availability ; Socioeconomic environment ; Ecosystems
(Location: IWMI HQ Call no: e-copy only Record No: H049142)
Agricultural land suitability analysis (ALSA) for crop production is one of the key tools for ensuring sustainable agriculture and for attaining the current global food security goal in line with the Sustainability Development Goals (SDGs) of United Nations. Although some review studies addressed land suitability, few of them specifically focused on land suitability analysis for agriculture. Furthermore, previous reviews have not reflected on the impact of climate change on future land suitability and how this can be addressed or integrated into ALSA methods. In the context of global environmental changes and sustainable agriculture debate, we showed from the current review that ALSA is a worldwide land use planning approach. We reported from the reviewed articles 69 frequently used factors in ALSA. These factors were further categorized in climatic conditions (16), nutrients and favorable soils (34 of soil and landscape), water availability in the root zone (8 for hydrology and irrigation) and socio-economic and technical requirements (11). Also, in getting a complete view of crop’s ecosystems and factors that can explain and improve yield, inherent local socio-economic factors should be considered. We showed that this aspect has been often omitted in most of the ALSA modeling with only 38% of the total reviewed article using socio-economic factors. Also, only 30% of the studies included uncertainty and sensitivity analysis in their modeling process. We found limited inclusions of climate change in the application of the ALSA. We emphasize that incorporating current and future climate change projections in ALSA is the way forward for sustainable or optimum agriculture and food security. To this end, qualitative and quantitative approaches must be integrated into a unique ALSA system (Hybrid Land Evaluation System - HLES) to improve the land evaluation approach.
5 Rana, V. K.; Suryanarayana, T. M. V. 2020. Performance evaluation of MLE [Maximum Likelihood Estimation], RF [Random Forest Tree] and SVM [Support Vector Machine] classification algorithms for watershed scale land use/land cover mapping using sentinel 2 bands. Remote Sensing Applications: Society and Environment, 19:100351. [doi: https://doi.org/10.1016/j.rsase.2020.100351]
Watersheds ; Land use mapping ; Land cover mapping ; Hydrology ; Models ; Performance evaluation ; Remote sensing ; Satellites ; Vegetation ; Cultivated land ; Rain ; Machine learning ; Principal component analysis ; Multivariate analysis / India / Gujarat / Vishwamitri Watershed
(Location: IWMI HQ Call no: e-copy only Record No: H049839)
(14.80 MB)
The land use and land cover map plays a significant role in agricultural, water resources planning, management, and monitoring programs at regional and national levels and is an input to various hydrological models. Land use and land cover maps prepared using satellite remote sensing techniques in conjunction with landform-soil-vegetation relationships and ground truth are popular for locating suitable sites for the construction of water harvesting structures, soil and water conservation measures, runoff computations, irrigation planning and agricultural management, analyzing socio-ecological concerns, flood controlling, and overall watershed management. Here we use a novel approach to analyze Sentinel–2 multispectral satellite data using traditional and principal component analysis based approaches to evaluate the effectiveness of maximum likelihood estimation, random forest tree, and support vector machine classifiers to improve land use and land cover categorization for Soil Conservation Service Curve Number model. Additionally, we use stratified random sampling to evaluate the accuracies of resulted land use and land cover maps in terms of kappa coefficient, overall accuracy, producer's accuracy, and user's accuracy. The classifiers were used for classifying the data into seven major land use and land cover classes namely water, built-up, mixed forest, cultivated land, barren land, fallow land with vertisols dominance, and fallow land with inceptisols dominance for the Vishwamitri watershed. We find that principal component analysis with support vector machine is able to produce highly accurate land use and land cover classified maps. Principal component analysis extracts the useful spectral information by compressing redundant data embedded in each spectral channel. The study highlights the use of principal component analysis with support vector machine classifier to improve land use and land cover classification from which policymakers can make better decisions and extract basic information for policy amendments.
6 Filgueiras, R.; Almeida, T. S.; Mantovani, E. C.; Dias, S. H. B.; Fernandes-Filho, E. I.; da Cunha, F. F.; Venancio, L. P. 2020. Soil water content and actual evapotranspiration predictions using regression algorithms and remote sensing data. Agricultural Water Management, 241:106346. [doi: https://doi.org/10.1016/j.agwat.2020.106346]
Soil water content ; Evapotranspiration ; Forecasting ; Remote sensing ; Irrigation management ; Decision making ; Vegetation index ; Water management ; Regression analysis ; Models ; Moderate resolution imaging spectroradiometer ; Machine learning / Brazil / Bahia
(Location: IWMI HQ Call no: e-copy only Record No: H049989)
(4.55 MB)
The application of technology and the development of data analysis, such as remote sensing and regression algorithms, are an easy and inexpensive way to estimate parameters related to water management, such as actual evapotranspiration (ETa) and soil water content (SWC). Therefore, the objective of this study was to predict the water management parameters with vegetation indices (VIs) and regression algorithms to enable irrigation management in a totally remote manner. The study was carried out in commercial maize areas irrigated by central pivots in the western part of the state of Bahia, Brazil. The MOD09GQ product was used to generate input data for the training models and to understand the phenology variations in the crops. The prediction of the dependent variables was tested using six regression algorithms, and the best algorithm was selected based on five statistical metrics. Among the regression models tested, the three that best fit the ETa and SWC data were RF (random forest), cubist (cubist regression), and GBM (gradient boosting machine), with slight superiority of cubist for the ETa and RF for the SWC. The fitted models for ETa and SWC showed the potential of VIs in providing information for irrigated agriculture and reinforcing the ability of regression algorithms in modelling the SWC and ETa variables. The findings make it possible to monitor irrigation efficiently with only the red and near infrared wavelengths, a fact that is considered the main contribution of this research to the practical and scientific communities.
7 Gaffoor, Z.; Pietersen, K.; Jovanovic, N.; Bagula, A.; Kanyerere, T. 2020. Big data analytics and its role to support groundwater management in the Southern African development community. Water, 12(10):2796. (Special issue: The Application of Artificial Intelligent in Hydrology) [doi: https://doi.org/10.3390/w12102796]
Groundwater management ; Data analysis ; SADC countries ; International waters ; Aquifers ; Data mining ; Machine learning ; Remote sensing ; Monitoring ; Technology ; Hydrological data ; Water levels ; Water storage ; Uncertainty ; Precipitation ; Social media ; Models / Southern Africa
(Location: IWMI HQ Call no: e-copy only Record No: H050040)
(1.58 MB) (1.58 MB)
Big data analytics (BDA) is a novel concept focusing on leveraging large volumes of heterogeneous data through advanced analytics to drive information discovery. This paper aims to highlight the potential role BDA can play to improve groundwater management in the Southern African Development Community (SADC) region in Africa. Through a review of the literature, this paper defines the concepts of big data, big data sources in groundwater, big data analytics, big data platforms and framework and how they can be used to support groundwater management in the SADC region. BDA may support groundwater management in SADC region by filling in data gaps and transforming these data into useful information. In recent times, machine learning and artificial intelligence have stood out as a novel tool for data-driven modeling. Managing big data from collection to information delivery requires critical application of selected tools, techniques and methods. Hence, in this paper we present a conceptual framework that can be used to manage the implementation of BDA in a groundwater management context. Then, we highlight challenges limiting the application of BDA which included technological constraints and institutional barriers. In conclusion, the paper shows that sufficient big data exist in groundwater domain and that BDA exists to be used in groundwater sciences thereby providing the basis to further explore data-driven sciences in groundwater management.
8 Oreggioni, F.; Garcia, S.; Gomez, M.; Mejia, A. 2021. A machine learning model of virtual water networks over time. Advances in Water Resources, 147:103819. [doi: https://doi.org/10.1016/j.advwatres.2020.103819]
Virtual water ; Water flow ; Machine learning ; Water footprint ; Water use ; Forecasting ; Models ; Performance evaluation ; Trade ; Case studies / USA
(Location: IWMI HQ Call no: e-copy only Record No: H050155)
(4.86 MB)
Virtual water flows are used to determine the indirect water requirements of a region or product, making them an indispensable tool for water sustainability analysis and assessment. Commodity flows are a key data needed to compute virtual water but are typically available every 5 years in the United States (US). The lack of continuous, annual commodity flow data severely limits our ability to study and understand the drivers, evolution, and alterations of virtual water in the US. We build and evaluate a machine learning model using Random Forest (RF) to predict annual commodity and virtual water flow networks. The model is used to perform several modeling experiments and illustrate the prediction of annual virtual water flows in the US during 2013–2018. We show that the RF predictions consistently outperform those from a gravity model. The overall performance of the RF algorithm improves as commodities or regions are aggregated into coarser groups. Likewise, the inclusion of past commodity flows as an additional explanatory variable enhances the RF performance. The combination of RF classification and regression allows predicting both network connections and flows without comprising performance. Based on our RF predictions for 2013–2018, we find that temporal variations in virtual water flows can be large for some regions in the US, underscoring the need addressed by this study of reconstructing domestic virtual water changes over time. By capturing inter-regional water consumption interactions in space and time, such reconstructed data could be beneficial in the future for anticipating and managing local and regional water scarcity.
9 Tague, C.; Frew, J. 2021. Visualization and ecohydrologic models: opening the box. Hydrological Processes, 35(1):e13991. [doi: https://doi.org/10.1002/hyp.13991]
Hydrology ; Models ; Data mining ; Machine learning ; Techniques ; Vegetation ; Evapotranspiration ; Stream flow ; Communication
(Location: IWMI HQ Call no: e-copy only Record No: H050200)
(15.10 MB)
Earth system models synthesize the science of interactions amongst multiple biophysical and, increasingly, human processes across a wide range of scales. Ecohydrologic models are a subset of earth system models that focus particularly on the complex interactions between ecosystem processes and the storage and flux of water. Ecohydrologic models often focus at scales where direct observations occur: plots, hillslopes, streams, and watersheds, as well as where land and resource management decisions are implemented. These models complement field-based and data-driven science by combining theory, empirical relationships derived from observation and new data to create virtual laboratories. Ecohydrologic models are tools that managers can use to ask “what if” questions and domain scientists can use to explore the implications of new theory or measurements. Recent decades have seen substantial advances in ecohydrologic models, building on both new domain science and advances in software engineering and data availability. The increasing sophistication of ecohydrologic models however, presents a barrier to their widespread use and credibility. Their complexity, often encoding 100s of relationships, means that they are effectively “black boxes,” at least for most users, sometimes even to the teams of researchers that contribute to their design. This opacity complicates the interpretation of model results. For models to effectively advance our understanding of how plants and water interact, we must improve how we visualize not only model outputs, but also the underlying theories that are encoded within the models. In this paper, we outline a framework for increasing the usefulness of ecohydrologic models through better visualization. We outline four complementary approaches, ranging from simple best practices that leverage existing technologies, to ideas that would engage novel software engineering and cutting edge human–computer interface design. Our goal is to open the ecohydrologic model black box in ways that will engage multiple audiences, from novices to model developers, and support learning, new discovery, and environmental problem solving.
10 Mukherjee, A.; Scanlon, B. R.; Aureli, A.; Langan, Simon; Guo, H.; McKenzie, A. A. (Eds.) 2021. Global groundwater: source, scarcity, sustainability, security, and solutions. Amsterdam, Netherlands: Elsevier. 676p.
Groundwater management ; Water resources ; Water scarcity ; Sustainability ; Water security ; Water availability ; Water supply ; Water governance ; Groundwater irrigation ; Groundwater pollution ; Water quality ; Contamination ; Chemical substances ; Pollutants ; Arsenic ; Groundwater recharge ; Aquifers ; Agricultural production ; Water storage ; International waters ; Water use efficiency ; Domestic water ; Surface water ; Brackish water ; Freshwater ; Desalination ; Environmental control ; Monitoring ; Climate change ; Drought ; Livelihoods ; Sustainable Development Goals ; Urbanization ; Arid zones ; Cold zones ; Hydrogeology ; Deltas ; River basins ; Technology ; Machine learning ; Modelling / Middle East / East Africa / South Asia / South Africa / Australia / USA / Brazil / China / Canada / Jamaica / Morocco / Israel / India / Pakistan / Bangladesh / Afghanistan / Lao People's Democratic Republic / Indonesia / Himalayan Region / North China Plain / Alberta / Texas / Florida / Cape Town / Medan / Barind Tract / Nile River Basin / Kingston Basin / Ganges-Brahmaputra-Meghna River Delta / Pearl River Delta
(Location: IWMI HQ Call no: IWMI Record No: H050267)
(0.18 MB)
11 Mishra, D.; Das, B. S.; Sinha, T.; Hoque, J. M.; Reynolds, C.; Islam, M. R.; Hossain, M.; Sar, P.; Menon, M. 2021. Living with arsenic in the environment: an examination of current awareness of farmers in the Bengal Basin using hybrid feature selection and machine learning. Environment International, 153:106529. (Online first) [doi: https://doi.org/10.1016/j.envint.2021.106529]
Drinking water ; Arsenic ; Contamination ; Awareness ; Farmers ; Farming systems ; Communities ; Socioeconomic environment ; Water supply ; Irrigation ; Public health ; Policies ; Machine learning ; Models / Bangladesh / India / Bengal Basin / West Bengal
(Location: IWMI HQ Call no: e-copy only Record No: H050292)
https://www.sciencedirect.com/science/article/pii/S0160412021001549/pdfft?md5=3520f677cef94fd26d81d0009caa2d29&pid=1-s2.0-S0160412021001549-main.pdf
https://vlibrary.iwmi.org/pdf/H050292.pdf
https://vlibrary.iwmi.org/pdf/H050292.pdf
(2.07 MB) (2.07 MB)
High levels of arsenic in drinking water and food materials continue to pose a global health challenge. Over 127 million people alone in Bangladesh (BD) and West Bengal (WB) state of India are exposed to elevated levels of arsenic in drinking water. Despite decades of research and outreach, arsenic awareness in communities continue to be low. Specifically, very few studies reported arsenic awareness among low-income farming communities. A comprehensive approach to assess arsenic awareness is a key step in identifying research and development priorities so that appropriate stakeholder engagement may be designed to tackle arsenic menace. In this study, we developed a comprehensive arsenic awareness index (CAAI) and identified key awareness drivers (KADs) of arsenic to help evaluate farmers’ preferences in dealing with arsenic in the environment. The CAAI and KADs were developed using a questionnaire survey in conjunction with ten machine learning (ML) models coupled with a hybrid feature selection approach. Two questionnaire surveys comprising of 73 questions covering health, water and community, and food were conducted in arsenic-affected areas of WB and BD. Comparison of CAAIs showed that the BD farmers were generally more arsenic-aware (CAAI = 7.7) than WB farmers (CAAI = 6.8). Interestingly, the reverse was true for the awareness linked to arsenic in the food chain. Application of hybrid feature selection identified 15 KADs, which included factors related to stakeholder interventions and cropping practices instead of commonly perceived factors such as age, gender and income. Among ML algorithms, classification and regression trees and single C5.0 tree could estimate CAAIs with an average accuracy of 84%. Both communities agreed on policy changes on water testing and clean water supply. The CAAI and KADs combination revealed a contrasting arsenic awareness between the two farming communities, albeit their cultural similarities. Specifically, our study shows the need for increasing awareness of risks through the food chain in BD, whereas awareness campaigns should be strengthened to raise overall awareness in WB possibly through media channels as deemed effective in BD.
12 Thomas, E.; Wilson, D.; Kathuni, S.; Libey, A.; Chintalapati, P.; Coyle, J. 2021. A contribution to drought resilience in East Africa through groundwater pump monitoring informed by in-situ instrumentation, remote sensing and ensemble machine learning. Science of the Total Environment, 780:146486. (Online first) [doi: https://doi.org/10.1016/j.scitotenv.2021.146486]
Groundwater ; Pumps ; Monitoring ; Drought ; Resilience ; Remote sensing ; Machine learning ; Surface water ; Water availability ; Forecasting / East Africa / Ethiopia / Kenya
(Location: IWMI HQ Call no: e-copy only Record No: H050328)
https://www.sciencedirect.com/science/article/pii/S0048969721015540/pdfft?md5=240defd015d08aab87e7de512401a767&pid=1-s2.0-S0048969721015540-main.pdf
https://vlibrary.iwmi.org/pdf/H050328.pdf
https://vlibrary.iwmi.org/pdf/H050328.pdf
(1.63 MB) (1.63 MB)
The prevalence of drought in the Horn of Africa has continued to threaten access to safe and affordable water for millions of people. In order to improve monitoring of water pump functionality, telemetry-connected sensors have been installed on 480 electrical groundwater pumps in arid regions of Kenya and Ethiopia, designed to improve monitoring and support operation and maintenance of these water supplies. In this paper, we describe the development and validation of two classification systems designed to identify the functionality and non-functionality of these electrical pumps, one an expert-informed conditional classifier and the other leveraging machine learning. Given a known relationship between surface water availability and groundwater pump use, the classifiers combine in-situ sensor data with remote sensing indicators for rainfall and surface water. Our validation indicates a overall pump status sensitivity (true positive rate) of 82% for the expert classifier and 84% for the machine learner. When the pump is being used, both classifiers have a 100% true positive rate performance. When a pump is not being used, the specificity (true negative rate) is about 50% for the expert classifier and over 65% for the machine learner. If these detection capabilities were integrated into a repair service, the typical uptime of pumps during drought periods in this region could potentially, if budget resources and institutional incentives for pump repairs were provided, result in a drought-period uptime improvement from 60% to nearly of 85% - a 40% reduction in the relative risk of pump downtime.
13 Tamiru, H.; Dinka, M. O. 2021. Application of ANN [Artificial Neural Networks] and HEC-RAS model for flood inundation mapping in Lower Baro Akobo River Basin, Ethiopia. Journal of Hydrology: Regional Studies, 36:100855. [doi: https://doi.org/10.1016/j.ejrh.2021.100855]
Flooding ; Mapping ; Hydrological modelling ; Neural networks ; Machine learning ; River basins ; Runoff ; Forecasting ; Rain ; Training / Ethiopia / Baro Akobo River Basin
(Location: IWMI HQ Call no: e-copy only Record No: H050485)
https://www.sciencedirect.com/science/article/pii/S2214581821000847/pdfft?md5=1534edf821b5ee38fa5413516a807b08&pid=1-s2.0-S2214581821000847-main.pdf
https://vlibrary.iwmi.org/pdf/H050485.pdf
https://vlibrary.iwmi.org/pdf/H050485.pdf
(7.58 MB) (7.58 MB)
Study region: Lower Baro River, Ethiopia.
Study focus: This paper presents the novelty of ANN and HEC-RAS model for flood inundation mapping in lower Baro Akobo Basin River, Ethiopia. ANN and HEC-RAS model is applied and successfully improves the accuracy of prediction and flood inundation in the region. This study uses 14 meteorological stations on a daily basis for 1999-2005 and 2006-2008 periods, and Topographical Wetness Index (TWI) to the train and test the model respectively. The runoff time series obtained in ANN model is linked to HEC-RAS and the flood depths were generated. The flood inundation generated in HEC-RAS model result was calibrated and validated in Normal Difference Water Index (NDWI).
New hydrological insights for the region: As the inundation map generated from the runoff values of ANN model reveals, the lower Baro river forms huge inundation depth up to 250 cm. The performance the ANN model was evaluated using Nash-Sutcliffe Efficiency (NSE = 0.86), PBIAS = 8.2 % and R2 = 0.91 and NSE = 0.88, PBIAS = 8.5 % and R2 = 0.93 during the training and testing periods respectively. The generated inundation areas in HEC-RAS and the water bodies delineated in NDWI were covered with 94.6 % and 96 % as overlapping areas during the calibration and validation periods respectively. Therefore, it is concluded that the integration of the ANN approach with the HEC-RAS model has improved the prediction accuracy in traditional flood forecasting methods.
Study focus: This paper presents the novelty of ANN and HEC-RAS model for flood inundation mapping in lower Baro Akobo Basin River, Ethiopia. ANN and HEC-RAS model is applied and successfully improves the accuracy of prediction and flood inundation in the region. This study uses 14 meteorological stations on a daily basis for 1999-2005 and 2006-2008 periods, and Topographical Wetness Index (TWI) to the train and test the model respectively. The runoff time series obtained in ANN model is linked to HEC-RAS and the flood depths were generated. The flood inundation generated in HEC-RAS model result was calibrated and validated in Normal Difference Water Index (NDWI).
New hydrological insights for the region: As the inundation map generated from the runoff values of ANN model reveals, the lower Baro river forms huge inundation depth up to 250 cm. The performance the ANN model was evaluated using Nash-Sutcliffe Efficiency (NSE = 0.86), PBIAS = 8.2 % and R2 = 0.91 and NSE = 0.88, PBIAS = 8.5 % and R2 = 0.93 during the training and testing periods respectively. The generated inundation areas in HEC-RAS and the water bodies delineated in NDWI were covered with 94.6 % and 96 % as overlapping areas during the calibration and validation periods respectively. Therefore, it is concluded that the integration of the ANN approach with the HEC-RAS model has improved the prediction accuracy in traditional flood forecasting methods.
14 Akpoti, K.; Higginbottom, T. P.; Foster, T.; Adhikari, R.; Zwart, Sander J. 2022. Mapping land suitability for informal, small-scale irrigation development using spatial modelling and machine learning in the Upper East Region, Ghana. Science of the Total Environment, 803:149959. [doi: https://doi.org/10.1016/j.scitotenv.2021.149959]
Farmer-led irrigation ; Small scale systems ; Land suitability ; Modelling ; Machine learning ; Food security ; Semiarid zones ; Groundwater ; Water availability ; Land use ; Land cover ; Soil properties ; Dry season ; Forecasting ; Reservoirs ; Population density ; Socioeconomic aspects / Ghana
(Location: IWMI HQ Call no: e-copy only Record No: H050670)
(7.61 MB)
Small-scale irrigation has gained momentum in recent years as one of the development priorities in Sub-Saharan Africa. However, farmer-led irrigation is often informal with little support from extension services and a paucity of data on land suitability for irrigation. To map the spatial explicit suitability for dry season small-scale irrigation, we developed a method using an ensemble of boosted regression trees, random forest, and maximum entropy machine learning models for the Upper East Region of Ghana. Both biophysical predictors including surface and groundwater availability, climate, topography and soil properties, and socio-economic predictors which represent demography and infrastructure development such as accessibility to cities and proximity to roads were considered. We assessed that 179,584 ± 49,853 ha is suitable for dry-season small-scale irrigation development when only biophysical variables are considered, and 158,470 ± 27,222 ha when socio-economic variables are included alongside the biophysical predictors, representing 77-89% of the current rainfed-croplands. Travel time to cities, accessibility to small reservoirs, exchangeable sodium percentage, surface runoff that can be potentially stored in reservoirs, population density, proximity to roads, and elevation percentile were the top predictors of small-scale irrigation suitability. These results suggested that the availability of water alone is not a sufficient indicator for area suitability for small-scale irrigation. This calls for strategic road infrastructure development and an improvement in the support to farmers for market accessibility. The suitability for small-scale irrigation should be put in the local context of market availability, demographic indicators, and infrastructure development.
15 Arabameri, A.; Pal, S. C.; Rezaie, F.; Nalivan, O. A.; Chowdhuri, I.; Saha, A.; Lee, S.; Moayedi, H. 2021. Modeling groundwater potential using novel GIS-based machine-learning ensemble techniques. Journal of Hydrology: Regional Studies, 36:100848. [doi: https://doi.org/10.1016/j.ejrh.2021.100848]
Groundwater potential ; Modelling ; Geographical information systems ; Machine learning ; Techniques ; Neural networks ; Remote sensing ; River basins ; Land use ; Land cover ; Landslides / Iran (Islamic Republic of) / Tabriz River Basin
(Location: IWMI HQ Call no: e-copy only Record No: H050645)
https://www.sciencedirect.com/science/article/pii/S221458182100077X/pdfft?md5=008d5c28c1313c1b111fb09896b85615&pid=1-s2.0-S221458182100077X-main.pdf
https://vlibrary.iwmi.org/pdf/H050645.pdf
https://vlibrary.iwmi.org/pdf/H050645.pdf
(14.10 MB) (14.1 MB)
Study region: The present study has been carried out in the Tabriz River basin (5397 km2) in north-western Iran. Elevations vary from 1274 to 3678 m above sea level, and slope angles range from 0 to 150.9 %. The average annual minimum and maximum temperatures are 2 °C and 12 °C, respectively. The average annual rainfall ranges from 243 to 641 mm, and the northern and southern parts of the basin receive the highest amounts.
Study focus: In this study, we mapped the groundwater potential (GWP) with a new hybrid model combining random subspace (RS) with the multilayer perception (MLP), naïve Bayes tree (NBTree), and classification and regression tree (CART) algorithms. A total of 205 spring locations were collected by integrating field surveys with data from Iran Water Resources Management, and divided into 70:30 for training and validation. Fourteen groundwater conditioning factors (GWCFs) were used as independent model inputs. Statistics such as receiver operating characteristic (ROC) and five others were used to evaluate the performance of the models.
New hydrological insights for the region: The results show that all models performed well for GWP mapping (AUC > 0.8). The hybrid MLP-RS model achieved high validation scores (AUC = 0.935). The relative importance of GWCFs was revealed that slope, elevation, TRI and HAND are the most important predictors of groundwater presence. This study demonstrates that hybrid ensemble models can support sustainable management of groundwater resources.
Study focus: In this study, we mapped the groundwater potential (GWP) with a new hybrid model combining random subspace (RS) with the multilayer perception (MLP), naïve Bayes tree (NBTree), and classification and regression tree (CART) algorithms. A total of 205 spring locations were collected by integrating field surveys with data from Iran Water Resources Management, and divided into 70:30 for training and validation. Fourteen groundwater conditioning factors (GWCFs) were used as independent model inputs. Statistics such as receiver operating characteristic (ROC) and five others were used to evaluate the performance of the models.
New hydrological insights for the region: The results show that all models performed well for GWP mapping (AUC > 0.8). The hybrid MLP-RS model achieved high validation scores (AUC = 0.935). The relative importance of GWCFs was revealed that slope, elevation, TRI and HAND are the most important predictors of groundwater presence. This study demonstrates that hybrid ensemble models can support sustainable management of groundwater resources.
16 Ahmed, M.; Mumtaz, R.; Zaidi, S. M. H. 2021. Analysis of water quality indices and machine learning techniques for rating water pollution: a case study of Rawal Dam, Pakistan. Water Supply, 21(6):3225-3250. [doi: https://doi.org/10.2166/ws.2021.082]
Water quality ; Water pollution ; Machine learning ; Techniques ; Monitoring ; Datasets ; Geographical information systems ; Chemicophysical properties ; Models ; Case studies / Pakistan / Islamabad / Rawal Dam
(Location: IWMI HQ Call no: e-copy only Record No: H050698)
https://iwaponline.com/ws/article-pdf/21/6/3225/933536/ws021063225.pdf
https://vlibrary.iwmi.org/pdf/H050698.pdf
https://vlibrary.iwmi.org/pdf/H050698.pdf
(0.99 MB) (0.99 MB)
Water Quality Index (WQI) is a unique and effective rating technique for assessing the quality of water. Nevertheless, most of the indices are not applicable to all water types as these are dependent on core physico-chemical water parameters that can make them biased and sensitive towards specific attributes including: (i) time, location and frequency for data sampling; (ii) number, variety and weights allocation of parameters. Therefore, there is a need to evaluate these indices to eliminate uncertainties that make them unpredictable and which may lead to manipulation of the water quality classes. The present study calculated five WQIs for two temporal periods: (i) June to December 2019 obtained in real time (using the Internet of Things (IoT) nodes) at inlet and outlet streams of Rawal Dam; (ii) 2012–2019 obtained from the Rawal Dam Water Filtration Plant, collected through GIS-based grab sampling. The computed WQIs categorized the collected datasets as ‘Very Poor’, primarily owing to the uneven distribution of the water samples that has led to class imbalance in the data. Additionally, this study investigates the classification of water quality using machine learning algorithms namely: Decision Tree (DT), k-Nearest Neighbor (KNN), Logistic Regression (LogR), Multilayer Perceptron (MLP) and Naive Bayes (NB); based on the parameters including: pH, dissolved oxygen, conductivity, turbidity, fecal coliform and temperature. The classification results showed that the DT algorithm outperformed other models with a classification accuracy of 99%. Although WQI is a popular method used to assess the water quality, there is a need to address the uncertainties and biases introduced by the limitations of data acquisition (such as specific location/area, type and number of parameters or water type) leading to class imbalance. This can be achieved by developing a more refined index that considers various other factors such as topographical and hydrological parameters with spatial temporal variations combined machine learning techniques to effectively contribute in estimation of water quality for all regions.
17 Yeditha, P. K.; Rathinasamy, M.; Neelamsetty, S. S.; Bhattacharya, B.; Agarwal, A. 2021. Investigation of satellite precipitation product driven rainfall-runoff model using deep learning approaches in two different catchments of India. Journal of Hydroinformatics, 22p. (Online first) [doi: https://doi.org/10.2166/hydro.2021.067]
Catchment areas ; Satellites ; Precipitation ; Rainfall-runoff relationships ; Models ; Neural networks ; Machine learning ; River basins ; Stream flow ; Forecasting / India / Vamsadhara River Basin / Mahanadhi River Basin
(Location: IWMI HQ Call no: e-copy only Record No: H050762)
https://iwaponline.com/jh/article-pdf/doi/10.2166/hydro.2021.067/974185/jh2021067.pdf
https://vlibrary.iwmi.org/pdf/H050762.pdf
https://vlibrary.iwmi.org/pdf/H050762.pdf
(1.23 MB) (1.23 MB)
Rainfall–runoff models are valuable tools for flood forecasting, management of water resources, and drought warning. With the advancement in space technology, a plethora of satellite precipitation products (SPPs) are available publicly. However, the application of the satellite data for the data-driven rainfall–runoff model is emerging and requires careful investigation. In this work, two satellite rainfall data sets, namely Global Precipitation Measurement-Integrated Multi-Satellite Retrieval Product V6 (GPM-IMERG) and Climate Hazards Group Infrared Precipitation with Station (CHIRPS), are evaluated for the development of rainfall–runoff models and the prediction of 1-day ahead streamflow. The accuracy of the data from the SPPs is compared to the India Meteorological Department (IMD)-gridded precipitation data set. Detection metrics showed that for light rainfall (1–10 mm), the probability of detection (POD) value ranges between 0.67 and 0.75 and with an increasing rainfall range, i.e., medium and heavy rainfall (10–50 mm and >50 mm), the POD values ranged from 0.24 to 0.45. These results indicate that the satellite precipitation performs satisfactorily with reference to the IMD-gridded data set. Using the daily precipitation data of nearly two decades (2000–2018) over two river basins in India's Eastern part, artificial neural network, extreme learning machine (ELM), and long short-time memory (LSTM) models are developed for rainfall–runoff modelling. One-day ahead runoff prediction using the developed rainfall–runoff modelling confirmed that both the SPPs are sufficient to drive the rainfall–runoff models with a reasonable accuracy estimated using the Nash–Sutcliffe Efficiency coefficient, correlation coefficient, and the root-mean-squared error. In particular, the 1-day streamflow forecasts for the Vamsadhara river basin (VRB) using LSTM with GPM-IMERG inputs resulted in NSC values of 0.68 and 0.67, while ELM models for Mahanadhi river basin (MRB) with the same input resulted in NSC values of 0.86 and 0.87, respectively, during training and validation stages. At the same time, the LSTM model with CHIRPS inputs for the VRB resulted in NSC values of 0.68 and 0.65, and the ELM model with CHIRPS inputs for the MRB resulted in NSC values of 0.89 and 0.88, respectively, in training and validation stages. These results indicated that both the SPPs could reliably be used with LSTM and ELM models for rainfall–runoff modelling and streamflow prediction. This paper highlights that deep learning models, such as ELM and LSTM, with the GPM-IMERG products can lead to a new horizon to provide flood forecasting in flood-prone catchments.
18 Yi, W. 2021. Forecast of agricultural water resources demand based on particle swarm algorithm. Acta Agriculturae Scandinavica, Section B - Soil and Plant Science, 14p. (Online first) [doi: https://doi.org/10.1080/09064710.2021.1990386]
Agriculture ; Water resources ; Water demand ; Forecasting ; Machine learning ; Algorithms ; Models ; Water footprint
(Location: IWMI HQ Call no: e-copy only Record No: H050818)
https://www.tandfonline.com/doi/pdf/10.1080/09064710.2021.1990386
https://vlibrary.iwmi.org/pdf/H050818.pdf
https://vlibrary.iwmi.org/pdf/H050818.pdf
(2.57 MB) (2.57 MB)
The planning and management of water resources are becoming more and more important, and the forecast of water demand as the prerequisite and foundation of the entire planning has become a very important task in agricultural development. This paper combines the particle swarm algorithm to construct the agricultural water resource demand forecasting model, analyzes the shortcomings of the traditional particle swarm algorithm, and makes appropriate improvements to the quantum particle swarm algorithm. Moreover, this paper constructs the functional structure of the agricultural water resource demand forecast model based on the forecast demand of water resources, and analyzes the application process of the particle swarm algorithm in the system of this paper. After the model is constructed, the performance of the model is verified, and the simulation test is designed to evaluate the effect of system forecast with actual data. At the same time, this paper uses the model constructed in this paper to analyze the factors affecting water resources forecast demand. From the results of the experimental analysis, it can be seen that the model constructed in this paper is more effective in the forecast of water resources demand.
19 Ghansah, B.; Foster, T.; Higginbottom, T. P.; Adhikari, R.; Zwart, Sander J. 2022. Monitoring spatial-temporal variations of surface areas of small reservoirs in Ghana’s Upper East Region using Sentinel-2 satellite imagery and machine learning. Physics and Chemistry of the Earth, 125:103082. [doi: https://doi.org/10.1016/j.pce.2021.103082]
(Location: IWMI HQ Call no: e-copy only Record No: H050847)
https://www.sciencedirect.com/science/article/pii/S147470652100125X/pdfft?md5=59bd7a98182c33a44b62aaf447495217&pid=1-s2.0-S147470652100125X-main.pdf
https://vlibrary.iwmi.org/pdf/H050847.pdf
https://vlibrary.iwmi.org/pdf/H050847.pdf
(9.19 MB) (9.19 MB)
Small reservoirs are one of the most important sources of water for irrigation, domestic and livestock uses in the Upper East Region (UER) of Ghana. Despite various studies on small reservoirs in the region, information on their spatial-temporal variations is minimal. Therefore, this study performed a binary Random Forest classification on Sentinel-2 images for five consecutive dry seasons between 2015 and 2020. The small reservoirs were then categorized according to landscape positions (upstream, midstream, and downstream) using a flow accumulation process. The classification produced an average overall accuracy of 98% and a root mean square error of 0.087 ha. It also indicated that there are currently 384 small reservoirs in the UER (of surface area between 0.09 and 37 ha), with 20% of them newly constructed between the 2016-17 and 2019-20 seasons. The study revealed that upstream reservoirs have smaller sizes and are likely to dry out during the dry season while downstream reservoirs have larger sizes and retain substantial amounts of water even at the end of the dry season. The results further indicated that about 78% of small reservoirs will maintain an average of 54% of their water surface area by the end of the dry season. This indicates significant water availability which can be effectively utilized to expand dry season irrigation. Overall, we demonstrate that landscape positions have significant impact on the spatial-temporal variations of small reservoirs in the UER. The study also showed the effectiveness of remote sensing and machine learning algorithms as tools for monitoring small reservoirs.
20 Brewer, K.; Clulow, A.; Sibanda, M.; Gokool, S.; Naiken, V.; Mabhaudhi, Tafadzwanashe. 2022. Predicting the chlorophyll content of maize over phenotyping as a proxy for crop health in smallholder farming systems. Remote Sensing, 14(3):518. [doi: https://doi.org/10.3390/rs14030518]
Maize ; Chlorophylls ; Plant health ; Forecasting ; Smallholders ; Farming systems ; Precision agriculture ; Machine learning ; Unmanned aerial vehicles / South Africa / KwaZulu-Natal / Swayimani
(Location: IWMI HQ Call no: e-copy only Record No: H050903)
(6.76 MB) (6.76 MB)
Smallholder farmers depend on healthy and productive crop yields to sustain their socio-economic status and ensure livelihood security. Advances in South African precision agriculture in the form of unmanned aerial vehicles (UAVs) provide spatially explicit near-real-time information that can be used to assess crop dynamics and inform smallholder farmers. The use of UAVs with remote-sensing techniques allows for the acquisition of high spatial resolution data at various spatio-temporal planes, which is particularly useful at the scale of fields and farms. Specifically, crop chlorophyll content is assessed as it is one of the best known and reliable indicators of crop health, due to its biophysical pigment and biochemical processes that indicate plant productivity. In this regard, the study evaluated the utility of multispectral UAV imagery using the random forest machine learning algorithm to estimate the chlorophyll content of maize through the various growth stages. The results showed that the near-infrared and red-edge wavelength bands and vegetation indices derived from these wavelengths were essential for estimating chlorophyll content during the phenotyping of maize. Furthermore, the random forest model optimally estimated the chlorophyll content of maize over the various phenological stages. Particularly, maize chlorophyll was best predicted during the early reproductive, late vegetative, and early vegetative growth stages to RMSE accuracies of 40.4 µmol/m-2 , 39 µmol/m-2 , and 61.6 µmol/m-2 , respectively. The least accurate chlorophyll content results were predicted during the mid-reproductive and late reproductive growth stages to RMSE accuracies of 66.6 µmol/m-2 and 69.6 µmol/m-2 , respectively, as a consequence of a hailstorm. A resultant chlorophyll variation map of the maize growth stages captured the spatial heterogeneity of chlorophyll within the maize field. Therefore, the study’s findings demonstrate that the use of remotely sensed UAV imagery with a robust machine algorithm is a critical tool to support the decision-making and management in smallholder farms.
Powered by DB/Text WebPublisher, from
