The present paper addresses a comprehensive historical assessment of water consumption, demand, and supply in Saudi Arabia, along with future projections regarding water balance, in terms of demand and supply by source in various sectors. Being an arid region, Saudi Arabia experiences scorching heat, low precipitation, a high rate of potential evaporation, and the absence of permanent water bodies over the territory. Groundwater contributes almost 61% of total available water, while the recharge rate is negligible. However, few widyan (ephemeral streams) systems exists to satisfy water demand, which could contribute to approximately one year of domestic water consumption if managed efficiently. The study also predicts water consumption scenarios for the next three consecutive development plans, i.e., the 10th plan (2015–2019), 11th plan (2020–2024), and 12th plan (2025–2029). The analysis shows that water consumption may decline significantly in the future, if the present rate of decline continues. Scenario I, if the current rate is assumed, provides a decrease in consumption of 14.36, 12.66, and 11.15 BCM for 10th, 11th, and 12th plans, respectively. Moreover, the domestic and industrial sectors will consume more water in the future. In the same way, scenarios II and III represent a decline in total water consumption, along with that of agriculture, while domestic and industrial water usage would increase, thus improving environmental sustainability.

Wind farm suitability analyses have been carried out to demarcate the potential zones in the Middle Zarafshan River basin. Uzbekistan’s major cities occupy the middle and lower Zarafshan Valley, which needs to allocate and develop wind energy farms to restore sustainability. In the current study, the Middle Zarafshan valley was assessed to provide a synoptic view of potential zones for wind energy. This study aimed to develop a geospatial method to identify optimal locations in the valley. To accomplish this task, five criteria were considered: wind speed, slope, distance from the transmission network, road network, land use, and land cover. Further, each criterion was assigned a weight according to expert opinions and published research outcomes. In addition, a maximum of 45 % weight was assigned to wind speed, followed by land use, land cover, slope, and others. Further, these criteria were categorized into four classes viz., unsuitable, less suitable, moderately suitable, and highly suitable. Further, different thematic layers were produced to realize this study. Wind speed maps were derived at different heights to calculate the results and integrate them with other derivatives. The findings of this study show that the maximum intensity of winds received at 100 m height or more, and more than 40 % area of the study area was estimated suitable for wind energy exploitation.

This study focuses on advancing precision agriculture through machine learning algorithms applied to crop classification using PlanetScope multispectral data in Kheda district, Gujarat. Three algorithms—Support Vector Machines (SVM), Spectral Angle Mapper (SAM), and Random Forests (RF)—were tested for their accuracy in classifying crop types. Additionally, the research utilized multi-temporal satellite imagery to monitor crop phenological cycles, enhancing classification reliability. The results highlighted SVM's boundary delineation, SAM's spectral similarity approach, and RF's ensemble learning as effective in distinguishing crops in mixed scenarios. Integrating ground truth data further validated classification accuracy, underscoring the study's contribution to improving agricultural management and planning.