Flood susceptibility mapping is essential for characterizing flood risk zones and for planning mitigation approaches. Using a multi-criteria decision support system, this study investigated a flood susceptible region in Bihar, India. It used a combination of the analytical hierarchy process (AHP) and geographic information system (GIS)/remote sensing (RS) with a cloud computing API on the Google Earth Engine (GEE) platform. Five main flood-causing criteria were broadly selected, namely hydrologic, morphometric, permeability, land cover dynamics, and anthropogenic interference, which further had 21 sub-criteria. The relative importance of each criterion prioritized as per their contribution toward flood susceptibility and weightage was given by an AHP pair-wise comparison matrix (PCM). The most and least prominent flood-causing criteria were hydrologic (0.497) and anthropogenic interference (0.037), respectively. An area of ~3000 sq km (40.36%) was concentrated in high to very high flood susceptibility zones that were in the vicinity of rivers, whereas an area of ~1000 sq km (12%) had very low flood susceptibility. The GIS-AHP technique provided useful insights for flood zone mapping when a higher number of parameters were used in GEE. The majorities of detected flood susceptible areas were flooded during the 2019 floods and were mostly located within 500 m of the rivers’ paths.

Twenty-two flood-causative factors were nominated based on morphometric, hydrological, soil permeability, terrain distribution, and anthropogenic inferences and further analyzed through the novel hybrid machine learning approach of random forest, support vector machine, gradient boosting, naïve Bayes, and decision tree machine learning (ML) models. A total of 400 flood and nonflood locations acted as target variables of the flood hazard zoning map. All operative factors in this study were tested using variance inflation factor (VIF) values (<5.0) and Boruta feature ranking (<10 ranks) for FHZ maps. The hybrid model along with RF and GBM had sound flood hazard zoning maps for the study area. The area under the receiver operating characteristics (AUROC) curve and statistical model matrices such as accuracy, precision, recall, F1 score, and gain and lift curve were applied to assess model performance. The 70%:30% sample ratio for training and validation of the standalone models concerning the AUROC value showed sound results for all the ML models, such as RF (97%), SVM (91%), GBM (97%), NB (96%), DT (88%), and hybrid (97%). The gain and lift curve also showed the suitability of the hybrid model along with the RF, GBM, and NB models for developing FHZ maps.

Crop selections and rotations are very important in optimising land and labour productivities, enhancing higher cropping intensities, producing better crop yield. A land suitability analysis system based on the analytical hierarchy process (AHP) technique coupled with the Geographic Information System (GIS) software environment can be a unique tool for better crop selection. The AHP-GIS technique was used in land suitability analysis in crop rotation decisions, for rice-jute (Kharif season) and potato-lentil (Rabi season) crops in the Hooghly District, West Bengal, India. The study area covering 291 ha was classified based on eight major soil nutrient levels with 70 randomly selected plots for soil sampling and analysis. The soil nutrient variability was examined with descriptive statistics followed by best semivariogram-based model selection for kriging interpolation in the ‘R’ software environment. The pairwise comparison matrix based ranking of parameters and giving weights was carried out considering the importance of each parameter for specific crops. The total area, being under the major rice-potato belt, could be classified from the suitability view point to the ‘highly suitable’(S₁) class occupying 29.2%, and ‘not suitable’ (N) class; 4.5% for rice, about 6.5% of land is ‘highly suitable’ (S₁), ‘and nearly 2.1% area is ‘not suitable’ (N) for jute; and 21.3% is ‘highly suitable’ (S₁) for potato and 12.4% for lentil crops. The yield maps showed nearly 75% and 90% of the area for rice and potato crops, respectively, gave sound crop yield. Furthermore, the GIS platform was used for crop rotation analysis to spread multiple seasons ensuring better crop management in long run. Overall, 25% of the rice crop area for jute in Kharif and 8% of potato crop area for lentil in the Rabi season were recommended as replacements.

A low-altitude remote sensing (LARS) system with an unmanned radio-controlled helicopter platform was used to acquire high-quality images of land and crop properties with higher spatial and temporal resolution. It is vital to visualize the relationship of LARS-based images with crop parameters, such as crop nutrient levels, etc. Five N-treatment (0, 33, 66, 99 and 132 kg ha^-1) rates with three replications each were arranged in a randomized manner for testing the LARS image acquisition system. Images were taken by the image acquisition unit of the system operated at a height of 20 m over the experimental plots. The coefficient of determination (r²) between N-treatments against NDVI_lars, NDVI_spectro, GNDVI_lars, and chlorophyll content estimated from leaf radiance values were in the range from 0.70 to 0.90, showing a high level of correlation between them. The test to verify the suitability of LARS-based images against spectrophotometer readings showed linear variation for the NDVI index with r² of 0.70 and 0.80 for 45-day-old and 65-day-old crops, respectively, Linear models were also developed to estimate chlorophyll content from NDVIlars and GNDVIlars index values, from the images, with better correlation for the latter (r² ≈ 0.82) and subsequently could determine the nitrogen deficiency level. The yield estimation model, with higher r² values of 0.95 and 0.98 for NDVI_lars and GNDVI_lars, respectively, further justified the suitability of the LARS system.