The prevention of soil salinization and managing agricultural irrigation depend greatly on accurately estimating soil salinity. Although the long-standing laboratory method of measuring salinity composition is accurate for determining soil salinity parameters, its use is frequently constrained by the high expense and difficulty of long-term in situ measurement. Soil salinity in the northern Nile Delta of Egypt severely affects agriculture sustainability and food security in Egypt. Understanding the spatial distribution of soil salinity is a critical factor for agricultural development and management in drylands. This research aims to improve soil salinity prediction by using a combined data collection method consisting of Sentinel-1 C radar data and Sentinel-2 optical data acquired simultaneously via integrated radar and optical sensor variables. The modelling approach focuses on feature selection strategies and regression learning. Feature selection approaches that include the filter, wrapper, and embedded methods were used with 47 selected variables depending on a genetic algorithm to scrutinize whether regions of the spectrum from optical indices and SAR texture choose the optimum combinations of selected variables. The sub-setting variables resulting from each feature selection method were used to train the regression learners’ random forest (RF), linear regression (LR), backpropagation neural network (BPNN), and support vector regression (SVR). Combining the BPNN feature selection method with the RF regression learner better predicted soil salinity (RME 0.000246; sub-setting variables = 18). Integrating different remote sensing data and machine learning provides an opportunity to develop a robust prediction approach to predict soil salinity in drylands. This research evaluated the performances of various machine learning models, overcame the limitations of conventional techniques, and optimized the variable input combinations. This research can assist farmers in soil-salinization-affected areas in better managing planting procedures and enhancing the sustainability of their lands.

In order to ensure the sustainability of production from agricultural lands, the degradation processes surrounding the fertile land environment must be monitored. Human-induced risk and status of soil degradation (SD) were assessed in the Northern-Eastern part of the Nile delta using trend analyses for years 2013 to 2023. SD hotspot areas were identified using time-series analysis of satellite-derived indices as a small fraction of the difference between the observed indices and the geostatistical analyses projected from the soil data. The method operated on the assumption that the negative trend of photosynthetic capacity of plants is an indicator of SD independently of climate variability. Combinations of soil, water, and vegetation’s indices were integrated to achieve the goals of the study. Thirteen soil profiles were dug in the hotspots areas. The soil was affected by salinity and alkalinity risks ranging from slight to strong, while compaction and waterlogging ranged from slight to moderate. According to the GIS-model results, 30% of the soils were subject to slight degradation threats, 50% were subject to strong risks, and 20% were subject to moderate risks. The primary human-caused sources of SD are excessive irrigation, poor conservation practices, improper utilisation of heavy machines, and insufficient drainage. Electrical conductivity (EC), exchangeable soil percentage (ESP), bulk density (BD), and water table depth were the main causes of SD in the area. Generally, chemical degradation risks were low, while physical risks were very high in the area. Trend analyses of remote sensing indices (RSI) proved to be effective and accurate tools to monitor environmental dynamic changes. Principal components analyses were used to compare and prioritise among the used RSI. RSI pixel-wise residual trend indicated SD areas were related to soil data. The spatial and temporal trends of the indices in the region followed the patterns of drought, salinity, soil moisture, and the difficulties in separating the impacts of drought and submerged on SD on vegetation photosynthetic capacity. Therefore, future studies of land degradation and desertification should proceed using indices as a factor predictor of SD analysis.

The accurate identification of extreme weather events (EWEs), particularly cyclones, has become increasingly crucial due to the intensifying impacts of climate change. In the Indian subcontinent, the frequency and severity of cyclones have demonstrably risen, highlighting the need for reliable detection methods to minimize casualties and economic losses. However, the inherent limitations of low-resolution data pose significant challenges to traditional detection methods. Deep learning models offer a promising solution, enabling the precise identification of cyclone boundaries crucial for assessing regional impacts using global climate models data. By leveraging the power of deep learning, we can significantly enhance our capabilities for cyclone detection and contribute to improved risk mitigation strategies in the vulnerable Indian subcontinent. Therefore, this paper introduces an edge-enhanced super-resolution GAN (EESRGAN) leveraging an end-to-end detector network. The proposed approach comprised of a generator network equipped by residual-in-residual dense block (RRDB) and discriminator containing Faster RCNN detector. The precise patterns of cyclone had been effectively extracted to help boundary detection. Extensive experiments have been conducted on Community Atmospheric Model (CAM5.1) data taken into account only seven variables. Four matrices including precision, recall, intersection over union, and mean average precision have been considered to assess the proposed approach. The results have been found very effective while achieving accuracy up to 86.3% and average precision (AP) of 88.63%. Moreover, the proposed method demonstrates its superiority while compared with benchmarks object detectors methods. Thus, the proposed method can be employed in the area of extreme climate detection and could enrich the climate research domain.