FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229455090> ?p ?o ?g. }

• W4229455090 endingPage "100773" @default.
• W4229455090 startingPage "100773" @default.
• W4229455090 abstract "Studies have focused on understanding land use/cover (LULC) change through regression techniques. However, machine learning (ML) techniques and their ensembles may provide more accurate results. Accurate determination of drivers of LULC can guide reliable land use planning and effective natural resource management. In this study, we tested the utility of ML techniques and ensemble modelling to explain the social-ecological drivers of LULC in the Okavango basin. The Deep Neural Network (DNN) coupled with climate-based regionalization of the study area were used for LULC classification of the years 2002, 2013 and 2020. Centroids of 22 LULC transitions of the same period were used to separately calibrate five (5) machine algorithms (namely Random Forests (RF), Gradient Boost Models (GBM) and Maximum Entropy (MaxEnt), Classification Tree Analysis (CTA) and their ensemble. Model performance was evaluated using the Receiver Operating Characteristic (ROC) and the True skill statistic (TSS). Variable importance was used to assess the contribution of social-ecological variables to each LULC transition. Variables that were determined to be driving LULC were then used to predict future LULC using the Artificial Neural Network and Cellular Automata (ANN-CA). Analysis results show that average LULC classification accuracy for the study period (2002, 2013 and 2020) was (Bsh Koppen zone; OA = 95.03, Kappa = 0.94), (Cwa Koppen zone; OA = 95.29, Kappa = 0.94), Cwb Koppen zone; OA = 96.04, Kappa = 0.95). The ML ensemble performed better (ROC> 95, TSS >87) than singular ML models based on two separate model evaluation metrics. The Random Forest classifier outperformed other singular ML (ROC = 90.41, TSS = 84.2). Based on the top-performing ensemble model, distance from rivers, population density, annual average temperature, drought severity, fire frequency and distance from towns influence the conversion of natural to anthropogenic LULC classes (importance >0.5). On the other hand, distance from rivers, soil organic carbon, precipitation, GDP, elevation, population density and annual average temperature importantly influenced conversion from one natural LULC class to another natural LULC class. The study revealed that natural classes (wetland, shrubland, water and woodlands) will gradually decrease at the expense of anthropogenic classes (built-up and cultivated) in future (2040). Despite proposing the necessity of a basin-wide land-use plan to minimise pressure on resources and ensure sustainable use, findings in this study illustrate the benefit of ensemble modelling in understanding LULC dynamics in transboundary basins." @default.
• W4229455090 created "2022-05-11" @default.
• W4229455090 creator A5024740858 @default.
• W4229455090 creator A5028543848 @default.
• W4229455090 creator A5070962325 @default.
• W4229455090 date "2022-08-01" @default.
• W4229455090 modified "2023-10-18" @default.
• W4229455090 title "Characterising social-ecological drivers of landuse/cover change in a complex transboundary basin using singular or ensemble machine learning" @default.
• W4229455090 cites W1512830467 @default.
• W4229455090 cites W1697635266 @default.
• W4229455090 cites W1756031276 @default.
• W4229455090 cites W1963804709 @default.
• W4229455090 cites W1964217023 @default.
• W4229455090 cites W1967400946 @default.
• W4229455090 cites W1968885079 @default.
• W4229455090 cites W1973361498 @default.
• W4229455090 cites W1977349531 @default.
• W4229455090 cites W1980233501 @default.
• W4229455090 cites W1981213426 @default.
• W4229455090 cites W1987352221 @default.
• W4229455090 cites W1996657311 @default.
• W4229455090 cites W1998025025 @default.
• W4229455090 cites W2000648382 @default.
• W4229455090 cites W2006104076 @default.
• W4229455090 cites W2009927598 @default.
• W4229455090 cites W2010524426 @default.
• W4229455090 cites W2019284143 @default.
• W4229455090 cites W2021527904 @default.
• W4229455090 cites W2027442956 @default.
• W4229455090 cites W2031443479 @default.
• W4229455090 cites W2033686454 @default.
• W4229455090 cites W2044609898 @default.
• W4229455090 cites W2051997212 @default.
• W4229455090 cites W2053885782 @default.
• W4229455090 cites W2054922660 @default.
• W4229455090 cites W2065100958 @default.
• W4229455090 cites W2065245252 @default.
• W4229455090 cites W2068064564 @default.
• W4229455090 cites W2071252970 @default.
• W4229455090 cites W2072381293 @default.
• W4229455090 cites W2074089694 @default.
• W4229455090 cites W2082163006 @default.
• W4229455090 cites W2084130313 @default.
• W4229455090 cites W2085959640 @default.
• W4229455090 cites W2092141482 @default.
• W4229455090 cites W2098000995 @default.
• W4229455090 cites W2101678239 @default.
• W4229455090 cites W2104301422 @default.
• W4229455090 cites W2104404130 @default.
• W4229455090 cites W2113410727 @default.
• W4229455090 cites W2127424770 @default.
• W4229455090 cites W2128827287 @default.
• W4229455090 cites W2139416101 @default.
• W4229455090 cites W2144109235 @default.
• W4229455090 cites W2153622281 @default.
• W4229455090 cites W2154506590 @default.
• W4229455090 cites W2158742799 @default.
• W4229455090 cites W2158770403 @default.
• W4229455090 cites W2160108534 @default.
• W4229455090 cites W2166116674 @default.
• W4229455090 cites W2168901396 @default.
• W4229455090 cites W2171653880 @default.
• W4229455090 cites W2176621583 @default.
• W4229455090 cites W2218047931 @default.
• W4229455090 cites W2261059368 @default.
• W4229455090 cites W2264205323 @default.
• W4229455090 cites W2320647263 @default.
• W4229455090 cites W2328167994 @default.
• W4229455090 cites W2338218472 @default.
• W4229455090 cites W2343168670 @default.
• W4229455090 cites W2402651011 @default.
• W4229455090 cites W2484955434 @default.
• W4229455090 cites W2511253820 @default.
• W4229455090 cites W2539666092 @default.
• W4229455090 cites W2586169538 @default.
• W4229455090 cites W2587456632 @default.
• W4229455090 cites W2590379360 @default.
• W4229455090 cites W2602023743 @default.
• W4229455090 cites W2614464134 @default.
• W4229455090 cites W2674804340 @default.
• W4229455090 cites W2716766686 @default.
• W4229455090 cites W2738705438 @default.
• W4229455090 cites W2753172916 @default.
• W4229455090 cites W2766922025 @default.
• W4229455090 cites W2804816412 @default.
• W4229455090 cites W281047273 @default.
• W4229455090 cites W2883476937 @default.
• W4229455090 cites W2889226858 @default.
• W4229455090 cites W2889302441 @default.
• W4229455090 cites W2900171934 @default.
• W4229455090 cites W2902486944 @default.
• W4229455090 cites W2904187459 @default.
• W4229455090 cites W2914673847 @default.
• W4229455090 cites W2914936460 @default.
• W4229455090 cites W2923688067 @default.
• W4229455090 cites W2943752364 @default.
• W4229455090 cites W2944005602 @default.
• W4229455090 cites W2944046454 @default.

• next