Your search found 2 records
1 Baran, E.; Jantunen, T.; Chheng, P. 2006. Developing a consultative Bayesian model for integrated management of aquatic resources: an inland coastal zone case study. In Hoanh, Chu Thai; Tuong, T. P.; Gowing, J. W.; Hardy, B. (Eds.). Environment and livelihoods in tropical coastal zones: managing agriculture, fishery, aquaculture conflicts. Wallingford, UK: CABI; Los Banos, Philippines: International Rice Research Institute (IRRI); Colombo, Sri Lanka: International Water Management Institute (IWMI) pp.206-218. (Comprehensive Assessment of Water Management in Agriculture Series 2)
Decision support tools ; Computer models ; Networks ; Water management ; Salt water intrusion ; Fish farming ; Rice ; Pesticides ; Food production / Vietnam / Bac Lieu
(Location: IWMI-HQ Call no: IWMI 639.8 G000 HOA Record No: H039117)
2 Phan, D. C.; Trung, T. H.; Truong, V. T.; Nasahara, K. N. 2022. Ensemble learning updating classifier for accurate land cover assessment in tropical cloudy areas. Geocarto International, 37(14):4053-4070. [doi: https://doi.org/10.1080/10106049.2021.1878292]
Land cover ; Land use ; Assessment ; Landsat ; Machine learning ; Time series analysis ; Remote sensing ; Satellite imagery ; Models / Vietnam / Mekong Delta / Soc Trang / Bac Lieu / Ca Mau / Kien Giang / Hau Giang
(Location: IWMI HQ Call no: e-copy only Record No: H051453)
https://www.tandfonline.com/doi/pdf/10.1080/10106049.2021.1878292
https://vlibrary.iwmi.org/pdf/H051453.pdf
https://vlibrary.iwmi.org/pdf/H051453.pdf
(4.82 MB) (4.82 MB)
Land use/cover information is fundamental for the sustainable management of resources. Notwithstanding the advancement of remote sensing, analysts daunt to generate sufficient-quality land use/cover products due to dense-cloud-contaminated and/or technical issues. This study proposes a novel approach (Ensemble Learning Updating Classifier/ELUC), which can be applied with various classification algorithms and data sets to simplistically generate new classifications or renew existing classifications with a remarkable accuracy improvement. Applying miscellaneous features of Landsat-8 images, the ELUC of a random-forest-based algorithm produces sequences of single-time classifications with a mean overall accuracy of 84%. Through the study period, these sequences of individual classifications were then joined to achieve a final classification which reaches an overall accuracy of 94%. Also, the ELUC of the random-forest-based algorithm outperforms that of Kernel-Density-Estimation with a 5% overall accuracy higher. These outcomes confirm the effectiveness of the ELUC for a remarkably consistent land use/cover estimation with a data-rich environment.
Powered by DB/Text WebPublisher, from
