The machine learning and geostatistical approach for assessment of arsenic contamination levels using physicochemical properties of water.

Arsenic contamination in groundwater due to natural or anthropogenic sources is responsible for carcinogenic and non-carcinogenic risks to humans and the ecosystem. The physicochemical properties of groundwater in the study area were determined in the laboratory using the samples collected across the Varanasi region of Uttar Pradesh, India. This paper analyses the physicochemical properties of water using machine learning, descriptive statistics, geostatistical and spatial analysis. Pearson correlation was used for feature selection and highly correlated features were selected for model creation. Hydrochemical facies of the study area were analyzed and the hyperparameters of machine learning models, i.e., multilayer perceptron, random forest (RF), naïve Bayes, and decision tree were optimized before training and testing the groundwater samples as high (1) or low (0) arsenic contamination levels based on the WHO 10 µg/L guideline value. The overall performance of the models was compared based on accuracy, sensitivity, and specificity value. Among all models, the RF algorithm outclasses other classifiers, as it has a high accuracy of 92.30%, a sensitivity of 100%, and a specificity of 75%. The accuracy result was compared to prior research, and the machine learning model may be used to continually monitor the amount of arsenic pollution in groundwater.

Assessment of hydrologic impact on flow regime due to dam inception using IHA framework.

In the last century, thousands of dams and diversions have been built to regulate the streamflow, resulting in water impoundment in the upstream and frequent drought conditions in the downstream. It has pressured researchers to study flow regime change and its complication on the downstream biota. The present study planned to develop a framework for trend analyzing of river flow and detecting flow regime change after the inception of Isapur and Arunavati dams, situated on the upstream side of Penganga bridge. Mann-Kendall (MK) and Sen's slope estimator for trend analysis and Indicators of Hydrologic Alteration (IHA) for flow regime alteration analysis were utilized. A total 26 parameters showed negatively altered flow regime with a magnitude varying from - 5.56 to - 100%. Fourteen altered parameters were modified drastically (more than 50% decrease) with the highest modification in 30-day maximum (100%) post-single dam inception. a total of 13 parameters were negatively altered with alteration value - 9.09 to - 86.36% post-double dam inception, out of which, three parameters were severely altered, with the highest alteration in the month of June. The period (1983-1994) was more altered than 1995-2016. This shows that Isapur dam has higher impact on flow regime change than Arunavati dam. Information about alteration of hydrological parameters will be helpful to improve the water flow regulation at Isapur and Arunavati dams for restoring river ecology on the downstream side.

Optimizing nutrient use efficiency, productivity, energetics, and economics of red cabbage following mineral fertilization and biopriming with compatible rhizosphere microbes.

Conventional agricultural practices and rising energy crisis create a question about the sustainability of the present-day food production system. Nutrient exhaustive crops can have a severe impact on native soil fertility by causing nutrient mining. In this backdrop, we conducted a comprehensive assessment of bio-priming intervention in red cabbage production considering nutrient uptake, the annual change in soil fertility, nutrient use efficiency, energy budgeting, and economic benefits for its sustainable intensification, among resource-poor farmers of Middle Gangetic Plains. The compatible microbial agents used in the study include Trichoderma harzianum, Pseudomonas fluorescens, and Bacillus subtilis. Field assays (2016-2017 and 2017-2018) of the present study revealed supplementing 75% of recommended NPK fertilizer with dual inoculation of T. harzianum and P. fluorescens increased macronutrient uptake (N, P, and K), root length, heading percentage, head diameter, head weight, and the total weight of red cabbage along with a positive annual change in soil organic carbon. Maximum positive annual change in available N and available P was recorded under 75% RDF + P. fluorescens + B. subtilis and 75% RDF + T. harzianum + B. subtilis, respectively. Bio-primed plants were also higher in terms of growth and nutrient use efficiency (agronomic efficiency, physiological efficiency, apparent recovery efficiency, partial factor productivity). Energy output (26,370 and 26,630 MJ ha-1), energy balance (13,643 and 13,903 MJ ha-1), maximum gross return (US $ 16,030 and 13,877 ha-1), and net return (US $ 15,966 and 13,813 ha-1) were considerably higher in T. harzianum, and P. fluorescens treated plants. The results suggest the significance of the bio-priming approach under existing integrated nutrient management strategies and the role of dual inoculations in producing synergistic effects on plant growth and maintaining the soil, food, and energy nexus.