Salinity hazard drives the alteration of occupation, land use and ecosystem service in the coastal areas: Evidence from the south-western coastal region of Bangladesh

Machine learning based recommendation of agricultural and horticultural crop farming in India under the regime of NPK, soil pH and three climatic variables

Machine learning (ML) can make use of agricultural data related to crop yield under varying soil nutrient levels, and climatic fluctuations to suggest appropriate crops or supplementary nutrients to achieve the highest possible production. The aim of this study was to evaluate the efficacy of five distinct ML models for a dataset sourced from the Kaggle repository to generate practical recommendations for crop selection or determination of required nutrient(s) in a given site. The datasets contain information on NPK, soil pH, and three climatic variables: temperature, rainfall, and humidity. The models namely Support vector machine, XGBoost, Random forest, KNN, and Decision Tree were trained using yields of individual data sets of 11 agricultural and 10 horticultural crops, as well as combined yield of both agri-horticultural crops. The results strongly suggest to evaluate individual data sets separately for each crop category rather than using combined the data sets of both categories for better predictions. Comparing the five ML models, the XGBoost demonstrated the highest level of accuracy. The precision rates of XGBoost for recommending agricultural crops, horticultural crops, and a combination of both were 99.09 % (AUC 1.0), 99.3 % (AUC 1.0), and 98.51 % (AUC 0.99), respectively. This non-intrusive method for generating crop recommendations in diverse environmental conditions holds the potential to provide valuable insights for the development of a user-friendly AI cloud-based interface. Such an interface would enable rapid decision-making for optimal fertilizer applications and the selection of suitable crops for cultivation at specific sites.

Identifying the interfaces between perceived multi-hazards and socio-ecological risks to strengthen local adaptations

Multi-hazards are a great concern in the present world. Likewise, the coastal part of Bangladesh is highly vulnerable to multi-hazards, including waterlogging, surface water salinity, land use change, prolonged dry seasons, and groundwater salinity. Multi-hazards and associated risks make local adaptations more difficult over time. Thus, the purpose of this study is to explore the connection between multi-hazards and their associated socio-ecological risks in the southwestern coastal part of Bangladesh. Mixed-methods approaches were used to collect all the data, and statistical analyses were performed to analyze the data. Results revealed that waterlogging significantly influenced local food access, poverty, child marriage, and divorce problems. Surface water salinity and land use change showed significant differences with the widening of salinity-affected areas. Waterlogging, land use change, and a prolonged dry season all showed significant differences in freshwater access. Prolonged dry seasons and groundwater salinity both have a significant impact on human health. Waterlogging and groundwater salinity significantly influence human migrations. These findings may strengthen local adaptation policies for salinity hazards, land use planning, household poverty, food access, livelihoods, water access, health effects, child marriage, and human migration. In addition, our findings indicate the potential to address the existing knowledge gaps pertaining to coastal hazards, risks, and adaptation issues.

Exploring Salinity Tolerance Mechanisms in Diverse Wheat Genotypes Using Physiological, Anatomical, Agronomic and Gene Expression Analyses

Salinity is a widespread abiotic stress that devastatingly impacts wheat growth and restricts its productivity worldwide. The present study is aimed at elucidating biochemical, physiological, anatomical, gene expression analysis, and agronomic responses of three diverse wheat genotypes to different salinity levels. A salinity treatment of 5000 and 7000 ppm gradually reduced photosynthetic pigments, anatomical root and leaf measurements and agronomic traits of all evaluated wheat genotypes (Ismailia line, Misr 1, and Misr 3). In addition, increasing salinity levels substantially decreased all anatomical root and leaf measurements except sclerenchyma tissue upper and lower vascular bundle thickness compared with unstressed plants. However, proline content in stressed plants was stimulated by increasing salinity levels in all evaluated wheat genotypes. Moreover, Na+ ions content and antioxidant enzyme activities in stressed leaves increased the high level of salinity in all genotypes. The evaluated wheat genotypes demonstrated substantial variations in all studied characters. The Ismailia line exhibited the uppermost performance in photosynthetic pigments under both salinity levels. Additionally, the Ismailia line was superior in the activity of superoxide dismutase (SOD), catalase activity (CAT), peroxidase (POX), and polyphenol oxidase (PPO) enzymes followed by Misr 1. Moreover, the Ismailia line recorded the maximum anatomical root and leaf measurements under salinity stress, which enhanced its tolerance to salinity stress. The Ismailia line and Misr 3 presented high up-regulation of H+ATPase, NHX2 HAK, and HKT genes in the root and leaf under both salinity levels. The positive physiological, anatomical, and molecular responses of the Ismailia line under salinity stress were reflected on agronomic performance and exhibited superior values of all evaluated agronomic traits.