Spatio-temporal patterns of land use and land cover change in Kibwezi West, Eastern Kenya DOI Creative Commons
Anne Omwoyo, Richard N. Onwonga,

Oliver Vivian Wasonga

et al.

Discover Soil., Journal Year: 2024, Volume and Issue: 1(1)

Published: Nov. 25, 2024

Kenyan drylands have over the years undergone extensive land use and cover (LULC) changes due to population increase, urbanization, agricultural expansion, industrialization infrastructural developments. There is however limited information on their historical future spatio-temporal patterns. This study assessed LULC change patterns in Kibwezi West for period 1990–2021 predicted map of 2051. Six classes (Forested land, shrubland, grassland, cropland, water body other lands) covering 1,040.9 Km2 were examined. Landsat imageries (1990, 2000, 2011 2021) classified using Random Forest algorithm R software, while was analyzed ERDAS Imagine. The 2051 Artificial Neural Network Cellular Automata algorithms. OpenLand software used visualization Sankey diagrams. Overall classification accuracy 78.04% obtained with 0.61 kappa coefficient. A net loss forested (−112.8 km2), shrubland (−54.48 km2) (−0.688 had occurred, a gain cropland (146.03 grassland (20.24 lands (1.66 between 1990–2021. Further, (−110.48 (−89.1 (−0.38 (−0.32 (176.90 (23.39 km2). pointed out encroachment into natural ecosystems like shrublands. findings this contribute knowledge dynamics drylands. These results will inform evidence-based decision-making processes sustainable planning, resource management environmental conservation efforts similar landscapes.

Language: Английский

Spatio-temporal patterns of land use and land cover change in Kibwezi West, Eastern Kenya DOI Creative Commons
Anne Omwoyo, Richard N. Onwonga,

Oliver Vivian Wasonga

et al.

Discover Soil., Journal Year: 2024, Volume and Issue: 1(1)

Published: Nov. 25, 2024

Kenyan drylands have over the years undergone extensive land use and cover (LULC) changes due to population increase, urbanization, agricultural expansion, industrialization infrastructural developments. There is however limited information on their historical future spatio-temporal patterns. This study assessed LULC change patterns in Kibwezi West for period 1990–2021 predicted map of 2051. Six classes (Forested land, shrubland, grassland, cropland, water body other lands) covering 1,040.9 Km2 were examined. Landsat imageries (1990, 2000, 2011 2021) classified using Random Forest algorithm R software, while was analyzed ERDAS Imagine. The 2051 Artificial Neural Network Cellular Automata algorithms. OpenLand software used visualization Sankey diagrams. Overall classification accuracy 78.04% obtained with 0.61 kappa coefficient. A net loss forested (−112.8 km2), shrubland (−54.48 km2) (−0.688 had occurred, a gain cropland (146.03 grassland (20.24 lands (1.66 between 1990–2021. Further, (−110.48 (−89.1 (−0.38 (−0.32 (176.90 (23.39 km2). pointed out encroachment into natural ecosystems like shrublands. findings this contribute knowledge dynamics drylands. These results will inform evidence-based decision-making processes sustainable planning, resource management environmental conservation efforts similar landscapes.

Language: Английский

Citations

2