ABSTRACT
[This corrects the article DOI: 10.3389/fpls.2023.1282217.].
ABSTRACT
An accurate assessment of nitrate leaching is important for efficient fertiliser utilisation and groundwater pollution reduction. However, past studies could not efficiently model nitrate leaching due to utilisation of conventional algorithms. To address the issue, the current research employed advanced machine learning algorithms, viz., Support Vector Machine, Artificial Neural Network, Random Forest, M5 Tree (M5P), Reduced Error Pruning Tree (REPTree) and Response Surface Methodology (RSM) to predict and optimize nitrate leaching. In this study, Urea Super Granules (USG) with three different coatings were used for the experiment in the soil columns, containing 1 kg soil with fertiliser placed in between. Statistical parameters, namely correlation coefficient, Mean Absolute Error, Willmott index, Root Mean Square Error and Nash-Sutcliffe efficiency were used to evaluate the performance of the ML techniques. In addition, a comparison was made in the test set among the machine learning models in which, RSM outperformed the rest of the models irrespective of coating type. Neem oil/ Acacia oil(ml): clay/sulfer (g): age (days) for minimum nitrate leaching was found to be 2.61: 1.67: 2.4 for coating of USG with bentonite clay and neem oil without heating, 2.18: 2: 1 for bentonite clay and neem oil with heating and 1.69: 1.64: 2.18 for coating USG with sulfer and acacia oil. The research would provide guidelines to researchers and policymakers to select the appropriate tool for precise prediction of nitrate leaching, which would optimise the yield and the benefit-cost ratio.
ABSTRACT
Sensor-based decision tools provide a quick assessment of nutritional and physiological health status of crop, thereby enhancing the crop productivity. Therefore, a 2-year field study was undertaken with precision nutrient and irrigation management under system of crop intensification (SCI) to understand the applicability of sensor-based decision tools in improving the physiological performance, water productivity, and seed yield of soybean crop. The experiment consisted of three irrigation regimes [I1: standard flood irrigation at 50% depletion of available soil moisture (DASM) (FI), I2: sprinkler irrigation at 80% ETC (crop evapo-transpiration) (Spr 80% ETC), and I3: sprinkler irrigation at 60% ETC (Spr 60% ETC)] assigned in main plots, with five precision nutrient management (PNM) practices{PNM1-[SCI protocol], PNM2-[RDF, recommended dose of fertilizer: basal dose incorporated (50% N, full dose of P and K)], PNM3-[RDF: basal dose point placement (BDP) (50% N, full dose of P and K)], PNM4-[75% RDF: BDP (50% N, full dose of P and K)] and PNM5-[50% RDF: BDP (50% N, full P and K)]} assigned in sub-plots using a split-plot design with three replications. The remaining 50% N was top-dressed through SPAD assistance for all the PNM practices. Results showed that the adoption of Spr 80% ETC resulted in an increment of 25.6%, 17.6%, 35.4%, and 17.5% in net-photosynthetic rate (Pn), transpiration rate (Tr), stomatal conductance (Gs), and intercellular CO2 concentration (Ci), respectively, over FI. Among PNM plots, adoption of PNM3 resulted in a significant (p=0.05) improvement in photosynthetic characters like Pn (15.69 µ mol CO2 m-2 s-1), Tr (7.03 m mol H2O m-2 s-1), Gs (0.175 µmol CO2 mol-1 year-1), and Ci (271.7 mol H2O m2 s-1). Enhancement in SPAD (27% and 30%) and normalized difference vegetation index (NDVI) (42% and 52%) values were observed with nitrogen (N) top dressing through SPAD-guided nutrient management, helped enhance crop growth indices, coupled with better dry matter partitioning and interception of sunlight. Canopy temperature depression (CTD) in soybean reduced by 3.09-4.66°C due to adoption of sprinkler irrigation. Likewise, Spr 60% ETc recorded highest irrigation water productivity (1.08 kg ha-1 m-3). However, economic water productivity (27.5 INR ha-1 m-3) and water-use efficiency (7.6 kg ha-1 mm-1 day-1) of soybean got enhanced under Spr 80% ETc over conventional cultivation. Multiple correlation and PCA showed a positive correlation between physiological, growth, and yield parameters of soybean. Concurrently, the adoption of Spr 80% ETC with PNM3 recorded significantly higher grain yield (2.63 t ha-1) and biological yield (8.37 t ha-1) over other combinations. Thus, the performance of SCI protocols under sprinkler irrigation was found to be superior over conventional practices. Hence, integrating SCI with sensor-based precision nutrient and irrigation management could be a viable option for enhancing the crop productivity and enhance the resource-use efficiency in soybean under similar agro-ecological regions.
