This study aimed to provide a systematic overview of the progress made in utilizing remote sensing for assessing the impacts of land use and land cover (LULC) changes on water resources (quality and quantity). This review also addresses research gaps, challenges, and opportunities associated with the use of remotely sensed data in assessment and monitoring. The progress of remote sensing applications in the assessment and monitoring of LULC, along with their impacts on water quality and quantity, has advanced significantly. The availability of high-resolution satellite imagery, the integration of multiple sensors, and advanced classification techniques have improved the accuracy of land cover mapping and change detection. Furthermore, the study highlights the vast potential for providing detailed information on the monitoring and assessment of the relationship between LULC and water resources through advancements in data science analytics, drones, web-based platforms, and balloons. It emphasizes the importance of promoting research efforts, and the integration of remote sensing data with spatial patterns, ecosystem services, and hydrological models enables a more comprehensive evaluation of water quantity and quality changes. Continued advancements in remote sensing technology and methodologies will further improve our ability to assess and monitor the impacts of LULC changes on water quality and quantity, ultimately leading to more informed decision making and effective water resource management. Such research endeavors are crucial for achieving the effective and sustainable management of water quality and quantity.

Weeds can significantly reduce productivity in agriculture (Roslim et al., 2021). Mechanical weeding and pesticides for tomatoes under irrigation are some of the weed management methods which are time-consuming and environmentally hazardous (Gerhards et al., 2022). Remote sensing and machine learning techniques offer more precise weed detection and management, using high-resolution satellite data and drones to identify early weed infestations and employ precision agriculture approaches (Su et al., 2022). This study uses machine learning to analyze drone images and map weeds in the Ha-Mphaila tomato irrigation scheme in South Africa, showcasing the potential of drones and machine learning for sitespecific weed management in agriculture.