Spatiotemporal change analysis of LULC using remote sensing and CA-ANN approach in the Hodna basin, NE of Algeria

Abstract

Spatiotemporal studies of land use/land cover change (LULCC) have become an important issue due to the rapid conversion of landscape and its impact on the environment and ecosystems. This study aims to identify the LULC change's impact on the Hodna basin (26,000 km2) from 2000 to 2020 using Landsat images data and forecast the possible change scenarios to the horizon of 2050. The Maximum Likelihood Supervised Classification (MLSC) was applied to Landsat data between 2000 and 2020 with a five-year interval. The confusion matrix of image classification indicates an overall accuracy of 85% and a kappa coefficients range between 0.82 and 0.96. To forecast the possible change scenarios of each class of LULC a transitional simulation using an artificial neural network (ANN) and machine learning algorithms. While, the cellular automata (CA) algorithm was used to simulate and predict the future LULC for the years 2030, 2040 and 2050 after validation of 2020 LULC map. The overall kappa calculated is 68.5% indicating a good accuracy of the validation process. The results show that for 2000–2020, agricultural lands decreased by 2.16% and sandy sails increased by 9.45%, indicating the expansion in the desertification phenomenon. Over the period 2000 to 2050, bare land decreased by 10% in 2015, recovered by 15% in 2020, and is projected to increase by 8% by 2050, reaching 73%; mixed and dense forest exhibited similar trends, growing from 0.7% in 2000 to 1.66% in 2050 with greater stability; built-up areas in the study zone surged by 150%, from 0.86% in 2000 to 2.5% in 2020, while clear forest remained relatively consistent, covering 4–6% of the surface; agricultural land diverged from bare land due to agricultural investment policies favoring new farms over bare land expansion. Urban sprawl is observed in the major cities like M'sila and Bordj Bou Arreridj and accelerated during the study period. Urban tissue evolved at the expense of agricultural land and focused mainly on slight slope areas and valleys.