In the race to enhance agricultural productivity, irrigation will become more dependent on poorly characterized and virtually unmonitored sources of water. Increased use of irrigation water has led to impaired water and soil quality in many areas. Historically, soil salinization and reduced crop productivity have been the primary focus of irrigation water quality. Recently, there is increasing evidence for the occurrence of geogenic contaminants in water. The appearance of trace elements and an increase in the use of wastewater has highlighted the vulnerability and complexities of the composition of irrigation water and its role in ensuring proper crop growth, and long-term food quality. Analytical capabilities of measuring vanishingly small concentrations of biologically-active organic contaminants, including steroid hormones, plasticizers, pharmaceuticals, and personal care products, in a variety of irrigation water sources provide the means to evaluate uptake and occurrence in crops but do not resolve questions related to food safety or human health effects. Natural and synthetic nanoparticles are now known to occur in many water sources, potentially altering plant growth and food standard. The rapidly changing quality of irrigation water urgently needs closer attention to understand and predict long-term effects on soils and food crops in an increasingly fresh-water stressed world.

The United States cotton industry is devoted to sustainable production strategies that reduce water, land, and energy consumption while enhancing soil health and cotton yield. Climate-smart agricultural solutions are being developed to increase yields and reduce operational costs. However, crop yield prediction is challenging because of the complex and nonlinear interactive effects of cultivar, soil type, management, pests and diseases, climate, and weather patterns on crops. To address this challenge, the machine learning (ML) method was used to predict yield, considering climatic change, soil diversity, cultivars, and fertilizer applications. Field data were collected over the southern US cotton belt in the 1980s and the 1990s. A second data source was generated from the process-based crop model GOSSYM to reflect the most recent effects of climate change over the last six years (2017–2022). We focused on nine locations in three southern states: Texas, Mississippi, and Georgia. The accumulated heat for each set of experimental data was used as an analogue for the time-series weather data to reduce the number of computations. The Random Forest (RF) regressor, Support Vector Regression (SVR), Light Gradient Boosting Machine (LightGBM) regressor, Multiple Linear Regression (MLR), and neural networks were evaluated. Cross-validation was performed to obtain an improved model that did not suffer from overfitting. The RF regressor achieved an accuracy of 97.75%, with an R ² of roughly 0.98 and a root mean square error of 55.05 kg/ha. The results demonstrate how a simple and robust model can be developed and utilized to help cotton climate-smart efforts.

Fertilizer N losses from agricultural systems have economic and environmental implications. Soil amendment with high C materials, such as coal char, may mitigate N losses. Char, a coal combustion residue, obtained from a sugar factory in Scottsbluff, NE, contained 29% C by weight. A 30‐d laboratory study was conducted to evaluate the effects of char addition on N losses via nitrous oxide (N₂O) emission, ammonia (NH₃) volatilization, and nitrate (NO₃–N) leaching from fertilized loam and sandy loam soils. Char was applied at five different rates (0, 6.7, 10.1, 13.4, and 26.8 Mg C ha⁻¹; char measured in C equivalent) to soils fertilized with urea ammonium nitrate (UAN) at 200 kg N ha⁻¹. In addition, there were two negative‐UAN control treatments: no char (no UAN) and char at 26.8 Mg C ha⁻¹ (no UAN). Treatment applied at 6.7 and 10.1 Mg C ha⁻¹ in fertilized sandy loam reduced NH₃ volatilization by 26–37% and at 6.7, 10.1, and 13.4 Mg C ha⁻¹ in fertilized loam soils by 24% compared with no char application. Nitrous oxide emissions and NO₃–N leaching losses were greater in fertilized compared with unfertilized soil, but there was no effect of char amendment on these losses. Because NO₃–N leaching loss was greater in sandy loam than in loam, soil residual N was twofold higher in loam than in sandy loam. This study suggests that adding coal char at optimal rates may reduce agricultural reactive N to the atmosphere by decreasing NH₃ volatilization from fertilized soils.