LULC change detection and future LULC modelling using RF and MLPNN-Markov algorithms in the uMngeni catchment, KwaZulu-Natal, South Africa DOI Creative Commons
Orlando Bhungeni, Michael Gebreslasie,

Ashadevi Ramjatan

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13

Published: April 30, 2025

Water catchment areas are the key strategic water sources with a variety of ecological benefits. However, trajectory Land Cover and Use Changes (LULC-C change poses significant threat to areas, negatively affecting quality. Thus, adoption remote sensing data Machine Learning Algorithms (MLAs) is novel approach that provides spatiotemporal on environmental changes resulting from LULC dynamics. Hence, this work harnessed Landsat imageries Random Forests (RF) classification as well hybrid model Multi-Layer Perceptron Markov chain (MLPNN-Markov) detect in forecast future changes. At every 5 years interval, RF generated more accurate maps for 2003–2023. The prediction 2019 also produced acceptable values kappa accuracy matrices, which were 65.50%, 58.4%, 90.90%, 0.52 overall accuracy, location, histogram, overall, respectively. findings highlighted decline forest strong negative correlation built-up mining areas. secondary invasion abandoned cropland occupied by grassland members was observed. displayed increasing trends between 2023. Wetlands water, however, exhibited steady trend minor variations. On other hand, each these persisted future, exception scaling-down behaviour 2032. outcomes will offer piece updated information LULC-C hints at possible direction This crucial local bodies tasked protect integrity aim improving

Language: Английский

Evaluating the performance of random forest, support vector machine, gradient tree boost, and CART for improved crop-type monitoring using greenest pixel composite in Google Earth Engine DOI
Chirasmayee Savitha, Reshma Talari

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(4)

Published: March 19, 2025

Language: Английский

Citations

0
LULC change detection and future LULC modelling using RF and MLPNN-Markov algorithms in the uMngeni catchment, KwaZulu-Natal, South Africa DOI Creative Commons
Orlando Bhungeni, Michael Gebreslasie,

Ashadevi Ramjatan

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13

Published: April 30, 2025

Water catchment areas are the key strategic water sources with a variety of ecological benefits. However, trajectory Land Cover and Use Changes (LULC-C change poses significant threat to areas, negatively affecting quality. Thus, adoption remote sensing data Machine Learning Algorithms (MLAs) is novel approach that provides spatiotemporal on environmental changes resulting from LULC dynamics. Hence, this work harnessed Landsat imageries Random Forests (RF) classification as well hybrid model Multi-Layer Perceptron Markov chain (MLPNN-Markov) detect in forecast future changes. At every 5 years interval, RF generated more accurate maps for 2003–2023. The prediction 2019 also produced acceptable values kappa accuracy matrices, which were 65.50%, 58.4%, 90.90%, 0.52 overall accuracy, location, histogram, overall, respectively. findings highlighted decline forest strong negative correlation built-up mining areas. secondary invasion abandoned cropland occupied by grassland members was observed. displayed increasing trends between 2023. Wetlands water, however, exhibited steady trend minor variations. On other hand, each these persisted future, exception scaling-down behaviour 2032. outcomes will offer piece updated information LULC-C hints at possible direction This crucial local bodies tasked protect integrity aim improving

Language: Английский

Citations

0