Crop identification is key to global food security. Due to the large scale of crop estimation, the science of remote sensing was able to do well in this field. The purpose of this study is to study the shortcomings and strengths of combined radar data and optical images to identify the type of crops in Tarom region (Iran). For this purpose, Sentinel 1 and Sentinel 2 images were used to create a map in the study area. The Sentinel 1 data came from Google Earth Engine’s (GEE) Level-1 Ground Range Detected (GRD) Interferometric Wide Swath (IW) product. Sentinel 1 radar observations were projected onto a standard 10-m grid in GRD output. The Sen2Cor method was used to mask for clouds and cloud shadows, and the Sentinel 2 Level-1C data was sourced from the Copernicus Open Access Hub. To estimate the purpose of classification, stochastic forest classification method was used to predict classification accuracy. Using seven types of crops, the classification map of the 2020 growth season in Tarom was prepared using 10-day Sentinel 2 smooth mosaic NDVI and 12-day Sentinel 1 back mosaic. Kappa coefficient of 0.75 and a maximum accuracy of 85% were reported in this study. To achieve maximum classification accuracy, it is recommended to use a combination of radar and optical data, as this combination increases the chances of examining the details compared to the single-sensor classification method and achieves more reliable information.

Plant health is the basis of agricultural development. Plant diseases are a major factor for crop losses in agriculture. Plant diseases are difficult to diagnose correctly, and the manual disease diagnosis process is time consuming. For this reason, it is highly desirable to automatically identify the diseases in strawberry plants to prevent loss of crop quality. Deep learning (DL) has recently gained popularity in image classification and identification due to its high accuracy and fast learning. In this research, deep learning models were used to identify the leaf scorch disease in strawberry plants. Four convolutional neural networks (SqueezeNet, EfficientNet-B3, VGG-16 and AlexNet) CNN models were trained and tested for the classification of healthy and leaf scorch disease infected plants. The performance accuracy of EfficientNet-B3 and VGG-16 was higher for the initial and severe stage of leaf scorch disease identification as compared to AlexNet and SqueezeNet. It was also observed that the severe disease (leaf scorch) stage was correctly classified more often than the initial stage of the disease. All the trained CNN models were integrated with a machine vision system for real-time image acquisition under two different lighting situations (natural and controlled) and identification of leaf scorch disease in strawberry plants. The field experiment results with controlled lightening arrangements, showed that the model EfficientNet-B3 achieved the highest classification accuracy, with 0.80 and 0.86 for initial and severe disease stages, respectively, in real-time. AlexNet achieved slightly lower validation accuracy (0.72, 0.79) in comparison with VGGNet and EfficientNet-B3. Experimental results stated that trained CNN models could be used in conjunction with variable rate agrochemical spraying systems, which will help farmers to reduce agrochemical use, crop input costs and environmental contamination.

Drought is a complex and poorly understood natural hazard in complex terrain and plains lie in foothills of Hindukush-Himalaya-Karakoram region of Central and South Asia. Few research studied climate change scenarios in the transboundary Chitral Kabul River Basin (CKRB) despite its vulnerability to global warming and importance as a region inhabited with more than 10 million people where no treaty on use of water exists between Afghanistan and Pakistan. This study examines the meteorological and agricultural drought between 2000 and 2018 and their future trends from 2020 to 2030 in the CKRB. To study meteorological and agricultural drought comprehensively, various single drought indices such as Precipitation Condition Index (PCI), Temperature Condition Index (TCI), Soil Moisture Condition Index (SMCI) and Vegetation Condition Index (VCI), and combined drought indices such as Scaled Drought Condition Index (SDCI) and Microwave Integrated Drought Index (MIDI) were utilized. As non-microwave data were used in MIDI, this index was given a new name as Non-Microwave Integrated Drought Index (NMIDI). Our research has found that 2000 was the driest year in the monsoon season followed by 2004 that experienced both meteorological and agricultural drought between 2000 and 2018. Results also indicate that though there exists spatial variation in the agricultural and meteorological drought, but temporally there has been a decreasing trend observed from 2000 to 2018 for both types of droughts. This trend is projected to continue in the future drought projections between 2020 and 2030. The overall study results indicate that drought can be properly assessed by integration of different data sources and therefore management plans can be developed to address the risk and signing new treaties.

The variability in soil properties and crop yield can be overcome by adoption of smart farming practices through interpolation and mapping of spatial variability patterns. Geospatial technologies can be utilized to determine the cause of spatial variability in fields for site-specific application of fertilizer. This study was designed to quantify and identify the spatial variation in soil properties and wheat (Triticum aestivum L.) yield and to delineate prescription maps for precise application of fertilizer in a semi-arid subtropical region of Pakistan. To examine the variability in soil properties on the production of the considered crop, this study comprised two different fields and each field was divided into (20 × 20 m) grids. The samples of soil were collected at 15 cm and 30 cm soil depths before the fertilization to analyze the different soil characteristics i.e., nitrogen (N), electrical conductivity (EC), potassium (K), soil organic matter (SOM), phosphorus (P), and pH. The boundaries of selected fields and grid points were established with a real-time kinematics-global positioning system (RTK-GPS). The soil data were acquired with a soil proximal sensor at a depth of 7 cm after fertilization. The statistical analysis coefficient of variation (CV), geostatistical-analysis-nugget-to-sill ratio (N:S), and the interpolated maps (ArcGIS pro 2.3) were used to characterize the least to moderate variability of soil parameters and yield, demanding site-specific management of fertilizer application. Cluster analysis was conducted using Minitab 21, which classified soil and yield characteristics into five categories: “very good”, “very low”, “good”, “poor”, and “medium”, with an external heterogeneity and internal homogeneity both more than 60%. Significant relationships (p < 0.05) between soil and crop properties were used to develop the management zones (MZs) for the precise application of fertilizer in wheat fields. Significant differences (p < 0.05) in soil nutrients were found in the very high and very low productivity zones at both sampling times, which suggest delineating the MZs for precise application of fertilizer according to the need of crop and soil properties. The results revealed that the optimum number of MZs for the wheat fields was five and there was heterogeneity in the soil nutrients in five MZs. The findings of this study also highlight the necessity of predicting the crop and soil factors by using precision technologies to develop the prescription maps, because sampling and analysis of soil are expensive and time-consuming. Based on the demand of the soil and crops, site-specific fertilization can increase economic and environmental efficiency.