Early detection of agricultural drought can alert farmers and authorities, enhancing the resilience of the food sector. A framework is proposed for developing a novel regional agricultural drought index (RegCDI) by combining remotely sensed vegetation health, soil moisture and crop water stress via a transparent Shannon’s entropy weighting method. The framework consists of the selection of suitable datasets based on their regional performance, the aggregation of selected drought indicators, the validation of the combined index against crop yield, and the testing of predictive capabilities. The creation and performance of RegCDI are demonstrated for the drought prone Indian state of Odisha. MODIS surface reflectance is selected for crop water stress and GLDAS-2 for assessing soil moisture deficits and vegetation health. Three selected indicators (SMCI, TCI, and SIWSI-1) are combined into RegCDI for Odisha. The performance of RegCDI is evaluated (a) against other popular drought indices and (b) by comparing with seasonal crop yields. RegCDI is used to identify drought hotspots based on drought severity, duration, and propensity over the study area. A reforecast evaluation of RegCDI (up to three months ahead) showed that the indicators based on soil moisture deficit and crop water stress could predict drought conditions up to two months ahead with no less than 80% accuracy. This demonstrated the potential of the RegCDI framework and its component indicators for early warning of drought in Odisha.

Pedotransfer functions (PTFs) are being instrumental in saturated hydraulic conductivity (K_s) estimation. Despite various advancements, the performance of existing generic K_s predicting PTFs need augmentation. This study developed a robust K_s predicting PTF using a machine learning (ML) algorithm and exhaustive data set for 324 soils with 28 properties sampled over a tropical savanna region of India. Four ML algorithms were evaluated for this purpose, and random forest (RF) outperformed all others. A substantial improvement to the prediction by RF‐based PTF was achieved through predictor selection using a hybrid wrapper‐embedded algorithm. The predictor selection algorithm selected eight pertinent predictors (HID‐S): S, Si, C, FSF, C_u, GMD, D₆₀, and D₁₀. The mean absolute error (MAE), root mean squared error (RMSE), coefficient of determination (R²), and Nash‐Sutcliffe efficiency (NSE) obtained as average tenfold cross‐validation scores for RF algorithm training with HID‐S were 0.87, 1.47, 0.94, and 0.94, respectively. The developed PTF (RF‐HID‐S) was evaluated alongside the recently published PTFs by Araya and Ghezzehei (2019, https://doi.org/10.1029/2018wr024357), within and outside the study region. In that process, it was observed that the RF‐HID‐S possessed superior prediction proficiency compared to the recently published and commonly used PTFs in both cases. These findings mark RF‐HID‐S as the most robust generalizable PTF, which may further be evaluated in different parts of the world. Moreover, looking at the performance of the eight selected predictors within and outside the study region, they can be considered for experiment design globally to make K_s estimation accurate and cost‐effective.