Anurag Malik

Accurate assessment of soil moisture is essential for enhancing irrigation efficiency and promoting sustainable agriculture. This study was conducted at Punjab Agricultural University, Ludhiana (PAU), to investigate the spatial and depth-wise variability of soil moisture across 30 field sites by using field measurements, geospatial-based (inverse distance weighting: IDW) interpolation, and machine learning techniques. Soil moisture was recorded at four depth intervals, including 0–15 cm, 15–30 cm, 30–45 cm, and 45–60 cm. The surface layer (0–15 cm) exhibited the highest variability due to evaporation and irrigation timing, with values ranging from 4.5% to 16.0%. Deeper layers showed more stable moisture retention, particularly at sites with intensive irrigation and crop cover, such as L11 (wheat), L22 (Gobhi Sarson), and L25 (wheat), where the moisture levels exceeded 14% at 45–60 cm depth, supporting suitability for deep-rooted crops. Supervised machine learning models, namely decision tree (DT), random forest (RF), and logistic regression (LR), were employed to classify soil moisture into low, medium, and high categories. The highest classification accuracy (88.9%) was achieved by the decision tree at 30–45 cm and logistic regression at 15–30 cm. Shallow layers exhibited frequent misclassification between medium and high classes, indicating surface-induced variability. Unsupervised clustering using K-means (k = 4) and hierarchical methods effectively delineated distinct soil moisture zones aligned with land use, irrigation history, and crop cover. The combination of geospatial analysis, depth-specific field data, and machine learning models provides an integrated framework for precision soil moisture assessment. This approach supports site-specific irrigation scheduling and water resource optimization, which are particularly critical for groundwater-stressed regions like Punjab. The novelty of this study lies in integrating depth-specific field-based soil moisture observations with geospatial interpolation and machine learning-based classification and clustering approaches to improve subsurface moisture characterization for precision irrigation management.

The present study was undertaken for six years to appraise the responses of four-year-old established grapevines (Vitis vinifera L., cv. Perlette) to saline–sodic groundwater irrigation in relation to different amendments in a field experiment on non-saline, non-sodic calcareous sandy loam soil under a semi-arid climate at the research farm of Punjab Agricultural University, Regional Research Station, Bathinda, Punjab, India. Different water quality treatments, viz., canal water or good-quality water (GQW), poor-quality saline–sodic groundwater (PQW), alternate irrigation of canal water and groundwater (GQW/PQW), PQW with 50% gypsum (CaSO₄·2H₂O) requirement (PQW + GR₅₀), PQW with 100% gypsum requirement (PQW + GR₁₀₀), and PQW with sulphitation pressmud (by-product of sugar industry) @ 6.6 t ha⁻¹ on a dry weight basis (PQW + SPM), applied in furrows, were imposed in quadruplicate with a randomized block design. PQW with an electrical conductivity (EC) of 2.2–2.4 dS m⁻¹, residual sodium carbonate (RSC) content of 6.21–6.44 mmolc L⁻¹, and a sodium adsorption ratio (SAR) from 23.1 to 24.8 (mmolc L⁻¹)^0.5 was used during the course of experimentation. The pooled mean 6-year data showcased that the treatments GQW/PQW, PQW + GR₅₀, PQW + GR₁₀₀, and PQW + SPM improved the berry yield by 28.3%, 11.3%, 21.2%, and 31.0%, respectively, when compared with PQW. Use of amendments, i.e., gypsum, sulphitation pressmud, and practice of GQW/PQW for irrigation in a cyclic mode, helped in reducing the pH, SAR, and bulk density (BD) of surface soil (0–15 cm) and enhancing the final infiltration rate (FIR) of soil and berry yield. A maximum water use efficiency (WUE) of 3.99 q ha⁻¹-cm was recorded in the GQW treatment, followed by 3.93, 3.72, and 3.68 q ha⁻¹-cm in the PQW + SPM, GQW/PQW, and PQW + GR₁₀₀ treatments, respectively. Application of amendments alongside PQW evidenced a significant enhancement in total soluble solids (TSSs) and a decrease in the acidity of berries as compared to PQW. These results suggest that table grape yield (cv. Perlette) on calcareous sandy loam soil under saline–sodic groundwater irrigation can be sustained with the application of PQW + GR₁₀₀, sulphitation pressmud, and GQW/PQW in already-established grapevines with minimal detrimental effects on soil health.

Knowledge of soil temperature (ST) is important for analysing environmental conditions and climate change. Moreover, ST is a vital element of soil that impacts crop growth as well as the germination of the seeds. In this study, four machine-learning (ML) paradigms including random forest (RF), radial basis neural network (RBNN), multi-layer perceptron neural network (MLPNN), and co-active neuro-fuzzy inference system (CANFIS) were used for estimation of daily ST at different soil depths (i.e. 5 cm: ST₅; 15 cm: ST₁₅; and 30 cm: ST₃₀) during 2016–2019 at Bathinda weather station, located in South-western Punjab (India). Five different combinations were formulated using four meteorological data, namely T_mean (mean air temperature), RH (relative humidity), WS (wind speed), and SSH (bright sunshine hours), and the optimal one was nominated by employing the gamma test (GT) for each soil depths, respectively. During the validation period, the outcomes of the RF, RBNN, MLPNN, and CANFIS models were evaluated according to performance metrics such as mean absolute error (MAE), root mean square error (RMSE), scatter index (SI), coefficient of efficiency (COE), Pearson correlation coefficient (PCC), and index of agreement (IOA), as well as through pictorial interpretation (Taylor diagram, box-whisker plots, time-variation, scatter plot, and radar chart). The comparison of the results of ML paradigms revealed the highest accuracy was achieved by the CANFIS model at all depths with MAE (RMSE) = 0.788, 0.636, 0.806 (1.074, 0.854, 1.041) °C, SI = 0.040, 0.033, 0.040, and COE (PCC)/IOA = 0.986, 0.991, 0.985 (0.994, 0.995, 0.993)/0.996, 0.998, 0.996. Thus, the results highlight the capability of the CANFIS model with T_mean, RH, WS, and SSH inputs for daily ST estimation at different soil depths on the study site.