Evaluation of river basins requires land-use and land-cover (LULC) change detection to determine hydrological and ecological conditions for sustainable use of their resources. This study assessed LULC changes over 28 years (1990–2018) in the Wami–Ruvu Basin, located in Tanzania, Africa. Six pairs of images acquired using Landsat 5 TM and 8 OLI sensors in 1990 and 2018, respectively, were mosaicked into a single composite image of the basin. A supervised classification using the Neural Network classifier and training data was used to create LULC maps for 1990 and 2018, and targeted the following eight classes of agriculture, forest, grassland, bushland, built-up, bare soil, water, and wetland. The results show that over the past three decades, water and wetland areas have decreased by 0.3%, forest areas by 15.4%, and grassland by 6.7%, while agricultural, bushland, bare soil, and the built-up areas have increased by 11.6%, 8.2%, 1.6%, and 0.8%, respectively. LULC transformations were assessed with water discharge, precipitation, and temperature, and the population from 1990 to 2018. The results revealed decreases in precipitation, water discharge by 4130 m3, temperature rise by 1 °C, and an increase in population from 5.4 to 10 million. For proper management of water-resources, we propose three strategies for water-use efficiency-techniques, a review legal frameworks, and time-based LULC monitoring. This study provides a reference for water resources sustainability for other countries with basins threatened by LULC changes.

No abstract

Conventional simulations on multi‐exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under‐utilized exits, especially with large numbers of pedestrians. We propose a multi‐exit evacuation simulation based on deep reinforcement learning (DRL), referred to as the MultiExit‐DRL, which involves a deep neural network (DNN) framework to facilitate state‐to‐action mapping. The DNN framework applies Rainbow Deep Q‐Network (DQN), a DRL algorithm that integrates several advanced DQN methods, to improve data utilization and algorithm stability and further divides the action space into eight isometric directions for possible pedestrian choices. We compare MultiExit‐DRL with two conventional multi‐exit evacuation simulation models in three separate scenarios: varying pedestrian distribution ratios; varying exit width ratios; and varying open schedules for an exit. The results show that MultiExit‐DRL presents great learning efficiency while reducing the total number of evacuation frames in all designed experiments. In addition, the integration of DRL allows pedestrians to explore other potential exits and helps determine optimal directions, leading to a high efficiency of exit utilization.