The escalating demand for green fodder, driven by the adoption of high-yielding livestock breeds and expansion of cooperative dairy farming, necessitates robust methods for monitoring fodder crop dynamics. Synthetic Aperture Radar (SAR), with its all-weather, day and night imaging capability, presents a promising tool for crop discrimination and forecasting. This study investigates the potential of time-series dual-polarized Sentinel-1 A SAR data for discriminating Kharif season fodder and non-fodder crops in three blocks of Banaskantha district, Gujarat, India, during July–October 2021. Polarimetric decomposition using the H/A/Alpha method was applied to derive temporal profiles of entropy, anisotropy, and alpha angle. Additionally, the Polarimetric Radar Vegetation Index (PRVI) was computed from Stoke’s parameters. Random Forest (RF) classifier which is an ensemble machine learning algorithm was employed to assess crop separability based on VV and VH backscatter intensities and derived polarimetric features. The temporal backscatter patterns varied distinctly across crop types: multi-cut fodder crops (e.g., napier, bajra) exhibited periodic peaks post-harvest, short-duration crops (e.g., cowpea) showed rapid rise and decline, while long-duration non-fodder crops (e.g., castor, groundnut) displayed gradual backscatter increase, peaking during vegetative to reproductive phases. Classification using combined polarimetric parameters (alpha, entropy, anisotropy) achieved the highest accuracy (93.5

Timely harvest detection and biomass estimation of Kharif fodder crops are critical for optimizing livestock feed supply and mitigating seasonal fodder deficits. This study focuses on Napier grass (Pennisetum purpureum × Pennisetum glaucum) in Gujarat, India, leveraging time-series Sentinel-1 SAR data to monitor crop phenology, detect multi-cut harvest events, and estimate above ground biomass. Sentinel-1C-band dual-polarized (VV, VH) data were acquired throughout the 2021 Kharif season, and field measurements of biomass, leaf area index (LAI), and soil moisture were conducted across 100 locations. Harvest events were identified via temporal dips in SAR backscatter and polarimetric parameters (VH, H/α decomposition, Polarimetric Radar Vegetation Index (PRVI)), revealing two to three harvests per plot with 96% classification accuracy. For biomass estimation, the Water Cloud Model (WCM) was parameterized and inverted using single-target Random Forest Regression (RFR), incorporating VV, VH, and VV/VH data. The sample size for biomass estimation was 80, while 20 samples were used for harvest validation. The VH polarization performed best during model calibration (R2 = 0.74), while combined VV-VH-VV/VH inputs improved biomass estimation accuracy (R2 = 0.86, RMSE = 0.724 kg/m2). The model’s performance was evaluated using 10- fold cross validation. These results highlight the potential of SAR-based approaches for promising site-specific fodder crop monitoring, supporting more efficient harvest planning and resource allocation in mixed farming systems.

This study used a geospatial approach to find appropriate structures and locations for rainwater collection in the Hathamati Basin, Panchamahal, Gujarat, India and covers total 1305.09 km2 area. The locations for five rainwater harvesting structures (check dams, farm ponds, percolation tanks, bench terraces and nala bunds) have been identified for possible runoff harvesting based on an integrated use of remote sensing and GIS. Sentinel 2 and SRTM DEM data have been used to process land-use layers in ENVI 4.7 environments and other thematic layers in ArcGIS environments. Weights have been assigned to each theme layer depending on the infiltration rate and runoff parameters. The best places for rainwater collection structures have been ranked in a layer created by applying a weighted overlay analysis. According to the findings, check dams, percolation tanks, bench terraces, nala bunds, and farm ponds can be built in 14, 3, 24, 60, and 61 locations throughout the entire basin, respectively. The suitability of these thematic maps will be useful to hydrologists, decision-makers, and planners for quickly identifying suitable sites with the highest potential for harvesting rainwater. The study shows how the GIS technique makes it easier to integrate thematic maps, which aids in identifying RWH structures.

Accurate identification and mapping of isabgol fields help in macro-level planning in the arid and semi-arid regions, where variability is very high due to erratic weather conditions, besides providing the production estimates of the crop. Isabgol is an important medicinal crop cultivated in western India. This study aims to accurately identify isabgol growing area at field level with help of progressive remotely sensed satellite data. Sentinel-2 data was used for the first crop season (2020) and the second crop season (2021) for the isabgol crop classification. Cluster to cluster comparison between satellite driven data and ground control point has been done for accuracy assessment. The producer accuracy ranged from 63.80 to 88.00% for the first crop (2020) and 70.84 to 88.89% for the second crop (2021). Our results were in sync with revenue records data (0.95 and 0.99 correlation for the first and second crop seasons, respectively). We found improved producer accuracy for the first crop over the second crop. The results shown that the time series Sentinel-2 data could be used for isabgol identification in various regions of India. The remote sensing-based methods could be used for precise estimation of isabgol crop acreage will help predict demand and supply. This information is valuable to the researchers, policy makers, pharmaceutical industries, and agronomists to accurately address issues related to import/ export of isabgol and price fixation.

Flooding is a major natural disaster in the Indian state of Bihar. The geographical setup of North Bihar increases the risk of floods and makes the region flood-prone. Recurring flood events in Bihar cause substantial loss of life and property every year. Rapid urbanization, deforestation, infrastructure development and erratic rainfall are the main causes of frequent floods in North Bihar. Public availability of geospatial datasets and free access to cloud-based geo-computing platform such as Google Earth Engine (GEE) are being commonly utilized for monitoring of flood events. The present work is aimed to examine the flood extent of the Kosi River Basin, Bihar and their impact on agricultural land using Sentinel-1 microwave and Sentinel-2A/B optical images. In this study, we found that a large portion of the Kosi River Basin was flooded during the monsoon season of 2020 and 2021. The inundation map has been prepared to visualize the extent of the flood, and it is expected that the results of the study can be used to inform decision-making by policymakers and other stakeholders to prioritize their efforts towards reducing the impact of floods and provide timely relief.

Floods are one of the most devastating natural disasters that cause immense damage to life, property and agriculture worldwide. Recurring floods in Bihar (a state in eastern India) during the monsoon season impact the agro-based economy, destroying crops and making it difficult for farmers to prepare for the next season. To mitigate the impact of floods on the agricultural sector, there is a need for early warning systems. Nowadays, remote sensing technology is used extensively for monitoring and managing flood events, which is also used in the present study. The random forest (RF) machine learning (ML) algorithm has also been used for land-use classification, and its output is used as an input for flood impact assessment. Here, we have analysed the flood extents and their impact on agriculture using Sentinel-1 form. The present study shows that floods severely impacted a large part of Bihar during the monsoon seasons of 2020 and 2021. About 701,967 ha of land (614,706 ha agricultural land) in 2020 and 955,897 ha (851,663 ha agricultural land) in 2021 were severely flooded. An to visualise the results, which can help the government authorities prioritize relief and rescue operations.

Image classification is an essential factor for crop mapping and identification. In recent years, many researchers focused on improving data mining/machine learning algorithms to more accurately deal with image classification and predictive problems. The publicly availability of geospatial datasets and free access to cloud-based geo-computing platforms such as Google Earth Engine (GEE) are widely being used for robust mapping and monitoring of crop phenology, acreage estimation and crop yield forecasting. In the present study, the maize (Zea mays) crop has been identified and acreage estimated using integrated Sentinel-2A/B and PlanetScope satellite data for the Rabi/ winter season of 2022 in the Indo-Gangetic Plain. In which, we have assessed and compared the performance of classification and regression trees (CART), support vector machine (SVM) and random forest (RF) algorithms of machine learning (ML) for acreage estimation of maize crops using Google’s GEE cloud computing platform. Wherein, we found that RF outperforms CART and SVM algorithms in the GEE platform with PlanetScope data (90.17% Overall Accuracy (OA) with Kappa 0.89) and also with the integration of PlanetScope and Sentinel-2A/B data (OA = 95.53%, Kappa 0.91). But, CART outperforms RF and SVM algorithms with Sentiel-2A/B data (OA = 88.59%, Kappa 0.85). We have also developed a web-based JavaScript code that can be tested anywhere in the world for robust mapping of crops under various climatic conditions. We expected that this study will be helpful for crop cultivation management, precision agriculture, crop insurance and for making a decision support system to prioritise the input subsidy for farmers.

Mapping, monitoring and estimation of fodder crop area can support farmers, policy makers to make right decisions in various conditions to improve the livestock productivity. The freely available high-resolution Sentinel-2 MSI data has increased the application of precision agriculture for a broader range. This study investigated the capabilities of Sentinel-2A/B MSI satellite data to identify and discriminate the fodder crops from other crops and estimate the area utilized for fodder cultivation in five districts of West Bengal during 2019–20 in rabi season (October to March). Multi-date NDVI based spectral profiles were generated from satellite imagery to ascertain the time of sowing which plays an important role to differentiate fodder crops from other crops. Image classification has been done through the ISODATA clustering technique. A field survey has been carried out in the study area and a total of 610 GT points were collected from different locations of fodder crops using handheld GPS and smartphone-based applications to validate the classification of crops. Accuracy assessment has also been performed between four classes (Fodder crops, Other crops, Forest and Waterbody) which is 81.61% for fodder crops, and 88.97% overall accuracy was observed in classification. The area under fodder cultivation was 0.68% of the total agricultural area, which has been estimated to the tune of 6.78 per thousand hectares. This study can be implemented for fodder crop identification and cultivation management plan to improve the livestock productivity by supply of fodder throughout the year.

In India, the adequate availability of green fodder is crucial for better milk production. However, the supply and demand gaps are huge for green fodder. To address this issue, an assessment of rabi fodder crops was conducted in Madhya Pradesh state of India. Satellite based assessment technique was used for fodder crops acreage estimation using a hybrid approach of classification method for rabi season crops (2019-20). Hierarchical decision rule method followed by, ISODATA (Iterative self-organizing data analysis technique) clustering approach were used for estimating fodder crops. Multi-date NDVI was derived from the imagery to generate temporal spectral profile for different crops using ground truth (GT) data. Total 510 GT points were collected and used for validation purposes by calculating the accuracy assessment of the classified image and overall, 81% accuracy of classification was obtained. Among the study areas, Rajgarh had the highest area under fodder cultivation, whereas lowest area was in Agar-Malwa district.

Estimating sugarcane ( Saccharum officinarum L. ) production at micro-scale prior to harvest is required for fixing of Fair and Remunerative Price (FRP) payable by sugar factories, levy price of sugar and its supply for public distribution systems and regulating supply of free-sale sugar. This may also help the sugar mill owners to plan for crushing the expected cane biomass, estimate the production of sugar in each mill and look for opportunities to sell or buy from nearest sugar mills if expected production is more or less than factory’s crushable capacity. A pilot-scale study was carried out in four sugar mills of Gujarat and Maharashtra states during 2017–2019 period. Multi-date multispectral data from LISS IV, LISS III of Resourcesat-2&2A, GPS and mobile-based ground truth data and Crop Cutting Experiment data (CCE) were used. Crop discrimination in the form of fresh and ratoon, field-scale crop health assessment, yield-model development and mill-level crop acreage and production estimation were carried out. LISS IV data along with error-free GPS-based polygons could lead to discrimination with 95% accuracy and between 88–91% with mobile-based point locations. The mill-level production was found to have less than 10% deviation from reported production. The field-scale assessment and enumeration could lead to mill-level crushable cane production forecast 2 months before harvest. Future efforts are needed to utilize agro-met products and SAR-based metrics to improve the production forecasting.

Feed and fodder comprises about 65% of the cost of milk production of a dairy industry. It is a crucial input for enhancing the milk production. To address the issue of fodder availability at first, its assessment is required. Thus, we have implemented remote sensing technique for fodder crop assessment at state level to create a baseline for fodder crop availability for dairy managers to plan for its procurement during deficit and for better management purposes during its excess. We have devised a technique for remote sensing-based fodder crop assessment based on spectral pattern of growth, i.e. normalised difference vegetation index profile and land surface wetness index profile of series of IRS LISS-III satellite data taken during the crop growth cycle for a hybrid method of crop classification. Second objective to address the issue of mitigating the deficit of fodder crops, we have demonstrated the satellite derived intersection of probable high soil wetness area and available current fallows during a crop growing season which can be utilised for growing fodder crops. For macro-level planning in a state for developing new fodder-growing areas, we have demonstrated the availability of soil wetness factor from SMAP data. Fallow land available between two cropping seasons can be identified through remote sensing for growing short duration fast growing fodder crops. This project has been a demonstration project for AMUL in Gujarat to implement it subsequently at national level.

This study highlights the application of multi-temporal Landsat-8 imageries to identify and discriminate fodder crops from food crops and estimate the area utilized for fodder cultivation in three districts of Haryana during 2016 in Rabi season. Atmospherically, corrected NDVI based spectral-temporal profiles showed that the time of sowing plays an important role to differentiate fodder crops from other crops. ISODATA unsupervised classification approach was used to image classification. Accuracy assessment was carried out between four classes (fodder crops, plantation, forest and other crops) and 91.49% as overall accuracy of classification was observed. The total area under fodder cultivation was estimated as 6.37 per thousand hectares (ha) with 3.60 per thousand hectares in Kurukshetra, 1.94 per thousand hectares in Ambala and 0.83 per thousand hectares in Yamunanagar. Thus it covered an area of approximately 4855 square kilometers which included Ambala, Krukshetra and Yamunanagar districts of Haryana.

Advancements in hyperspectral remote sensing technology have opened new avenues to explore innovative ways to map crops in terms of area and health. To study precise mapping of agriculture and horticulture crops along with biophysical and biochemical constituents at field scale, an airborne AVIRIS-NG hyperspectral imaging has been conducted in various agro-climatic regions representing diverse agricultural types of India. Crop classification with available and developed algorithms has been applied over homogeneous and heterogeneous agriculture and horticulture cropped areas. The spectral angle mapper and maximum likelihood algorithms showed classification accuracy of 77%-94% for AVIRI-NG and 42%-55% for LISS IV. The customized deep neural network and maximum noise function (MNF)-based classification schemes showed an accuracy of 93% and 86% for mapping of agriculture and horticulture crops respectively. The forward and inversion of canopy radiative transfer model protocol was developed for retrieval of crop parameters such as leaf area index (LAI) and chlorophyll content (C-ab) using AVIRIS-NG narrow bands. The retrieved LAI and C-ab showed 19%-27% and 23%-29% deviation from measured mean for homogeneous and heterogeneous agricultural areas respectively. Red edge position index-based empirical model and multivariate linear regression of multiple indices showed maximum correlation of 0.62 and 0.93 respectively, to map leaf nitrogen content. Water condition index was developed using vegetation and water indices to distinguish crop water-based abiotic stress. Wheat yellow rust disease has been identified at field scale using absorption band depth analysis at 662-702 and 2155-2175 nm, and further applied to AVIRIS-NG data to detect biotic stress at spatial scale. This study establishes that such missions have the potential to boost accurate mapping of economically valuable minor crops and generate health indicators to distinguish biotic and abiotic stresses at field scale.

Identification of crop and its accuracy is an important aspect in predicting crop production using Remote Sensing technology. This study investigates the ability of Support Vector Machine (SVM) algorithm in discriminating fodder crops and estimating its area using moderate resolution multi-temporal Landsat-8 OLI data. SVM is a non-parametric statistical learning method and its accuracy is dependent on the parameters and the kernels used. The objective was to evaluate the feasibility of SVM in fodder classification and compare the results with traditional parametric Maximum Likelihood Classification (MLC). Fodder crops are available over small fields in the study area thus having large number of pure fodder pixels over small area is difficult. Hence, SVM has an advantage over MLC as it works well with less training data sets also. Three kernels (linear, polynomial and radial based function) were used with SVM classification. Comparative analysis showed that higher overall accuracy was observed in SVM in comparison to MLC. Temporal change in the spectral properties of the crops derived through Normalized Difference Vegetation Index (NDVI) from multi-temporal Landsat-8 was found to be the most important information that affects accuracy of classification. The classification accuracies for SVM with radial based function, polynomial, linear kernel and MLC were 90.09%, 89.9%, 88.9% and 82.4% respectively. The result suggested that SVM including three kernels performed significantly better than MLC. India has low livestock productivity due to unavailability of fodder hence this study could help in strengthening the fodder productivity.

Assessing the nature and extent of damage due to natural calamities remains one of the thrust areas in monitoring resource inventory through remote sensing. The effect of the cyclone Phailin and the post-incessant rains during second fortnight of October 2013 on coastal Odisha was studied in terms of rice area flooded, submerged and damaged. Multi-temporal SAR data were analysed to obtain the rice mask, and from this rice mask, the flood affected rice area was determined. Taluka-wise and district-wise crop loss proportion was estimated, and the overall production loss has been estimated. SAR data aided in delineation of flooded regions, while AWiFS NDVI data of subsequent dates showed both continued inundation and crop vigour status post-flood time period. The ground truth indicated that a major portion of the inundated region was not rice but was typha grasses and harvested rice field which should not be accounted as damage to rice crop. The damage on crop yield was difficult to assess; however, the inundation of the crop at panicle initiation and flowering would have impact on grain filling (results in chaffiness) and was considered as completely damaged. Most of the current inundated rice regions fall in this category. It was estimated that a total of 0.167 million hectares and 0.37 million tons of rice crop was lost in the cyclone and floods. The district-level percentage area of rice flooded was communicated to State Remote Sensing Centre in four days timeframe. The overall accuracy obtained for the validation of the ground truth sites was 91.5 %.

Detection of crop stress is one of the major applications of remote sensing in agriculture. Many researchers have confirmed the ability of remote sensing techniques for detection of pest/disease on cotton. The objective of the present study was to evaluate the relation between the mealybug severity and remote sensing indices and development of a model for mapping of mealybug damage using remote sensing indices. The mealybug-infested cotton crop had a significantly lower reflectance (33%) in the near infrared region and higher (14%) in the visible range of the spectrum when compared with the non-infested cotton crop having near infrared and visible region reflectance of 48 % and 9% respectively. Multiple Linear regression analysis showed that there were varying relationships between mealybug severity and spectral vegetation indices, with coefficients of determination (r2) ranging from 0.63 to0.31. Model developed in this study for the mealybug damage assessment in cotton crop yielded significant relationship (r2=0.863) and was applied on satellite data of 21st September 2009 which revealed high severity of mealybug and it was low on 24th September 2010 which confirmed the significance of the model and can be used in the identification of mealybug infested cotton zones. These results indicate that remote sensing data have the potential to distinguish damage by mealybug and quantify its abundance in cotton.

Remote sensing technology becomes an effective and inexpensive technique for detecting disease in vegetation. In this study, an attempt has been done to discriminate healthy and late blight affected crop using remote sensing based indices such as NDVI and LSWI. NDVI and LSWI spectral profiles between healthy and late blight affected crop shows large difference. Mean difference in reflectance between two acquired dates Jan. 10 and 29, 2009 crop clusters varied from 31.28 % in red band, 7.7 % in NIR band and 6.23 % in SWIR bands in healthy crops while in late blight affected crops it is −15.5 % in red, 44.4 % in NIR and −14.61 % in SWIR bands. Negative percentage differences in reflectance indicate reflectance increases from Jan. 10, 2009 to Jan. 29, 2009, while positive difference indicate decrease in reflectance between the two dates. Since potato is an irrigated crop, these differences in reflectance are attributed to prevalent disease at that time. It is found that severely affected areas are Bardhman, Arambag, Bishnupur, Ghatal and Hugli taluka with crop damage areas are 4036.66, 1138.68, 2025.23, 469.15, and 380.08 ha, respectively.

Objective of this study was to identify stripe rust affected areas of wheat crop as well as evaluation of remote sensing (RS) derived indices. Moderately low temperature and high humidity favour the growth of yellow rust. Most affected areas of Punjab are the foothill districts such as Gurdaspur, Hoshiarpur and Ropar. Occurrence of yellow rust is possible when maximum temperature for day is below 15 °C and Temperature difference of day’s maximum and minimum temperature is less than 5 °C during the early growth of wheat. Forecast of the infestation was done using 3 days forecast of weather data obtained from Weather Research and Forecasting (WRF) model at 5 km resolution. Weather forecast used was obtained from Meteorological and Oceanographic Satellite Data Archival System (MOSDAC) site and post infestation, identification of specific locations were done using multi-date IRS AWiFS data. It is an attempt for early detection through 3 days advance forewarning of weather which will be handy tool for planners to expedite relief measures in case of epidemic with a more focused zones of infestation as well as for crop insurers to know the location and extent of damage affected areas.

Crop coefficient values are used to estimate crop evapotranspiration (ETc) for determining irrigation scheduling. Many important crop biophysical properties such as Percentage Vegetation Cover and Leaf Area Index can be estimated from remotely sensed Vegetation Index, in order to quantify real time vegetation growth dynamics. The objective of this study was to understand the effectiveness of basal crop coefficient (Kcb) values estimated from remote sensing and their application in real time crop water requirement. The study was carried out for Cotton crop in Sirsa district of Haryana. Spectral index such as SAVI (Soil Adjusted Vegetation Index) and Fractional Vegetation Cover (Fc) were used to estimate Kcb value. High spatial resolution Landsat TM5 images were used to generate spectral profile of NDVI, SAVI and Fc for different crop cover. Using, available empirical models from literature, crop coefficient was derived from SAVI values. Reference Crop Evapotranspiration (ET0) was estimated using Blaney-Criddle Method, taking weather data from ICAR Research Station Observatory. The crop coefficients derived from Remote Sensing data were used along with ET0 values to estimate crop evapotranspiration (ETc). The result showed that the spatial distribution of seasonal ETc varied between 317 to 534 mm for growing season of cotton depending upon sowing date and other condition. The estimated crop evapo-transpiration (ETc) pattern was compared with fractional vegetation cover. Spatial distribution map of cotton ETc, basal crop coefficient and fractional vegetation cover showed areas of high and low water demand. This work can help in water management practices for better irrigation management. S.K. Singh et al 524