In India, spatial and temporal variation of precipitation has been boundless varying from 11000 mm to 90 mm. The average annual per capita water availability has declined from 5000 cubic meter in year 1950 to 1545 cubic meter in year 2011 and estimated to reduce further to 1341 and 1140 cubic meter in year 2025 and 2050, respectively. Agriculture sector, which provide 54.6% of total employment to growing population, alone consumes more than 90% of total groundwater draft in irrigation. Over the years, groundwater has become dominant source of irrigation due to its independent access and timely availability of water. This outrageous dependency on groundwater has led to depletion of water table in 64% district of the country between TE2002 and TE2016. With collective efforts of government at various levels, utilized irrigated potential including both surface and ground water has increased to 87 Mha while ultimate irrigation potential touched 140 Mha. In context of rapid depletion of water resources, there is need to increase water use efficiency. Efficient method, like microirrigation, can play pivotal role in management of irrigation water demand. Properly designed and managed drip and sprinkler irrigation system have irrigation efficiency about 90% and 70%, respectively contrast to surface irrigation method which have just about 40%. Recognizing the gravity of water scarcity in many part of the country, government has started formulating its water policy pivotal to micro irrigation. In year 2015, government has bundled all ongoing irrigation schemes into Pradhan Mantri Krishi Sinchayee Yojna (PMKSY) in which micro irrigation as an integral component. The successful adoption of water efficient technologies has two preconditions namely technical know-how and its accessibility through institutional support systems. Government has taken many initiatives to intensify outreach of efficient irrigation technology to farm.

Computer vision with deep learning is emerging as a significant approach for non-invasive and non-destructive plant phenotyping. Spikes are the reproductive organs of wheat plants. Detection and counting of spikes considered the grain-bearing organ have great importance in the phenomics study of large sets of germplasms. In the present study, we developed an online platform, “Web-SpikeSegNet,” based on a deep-learning framework for spike detection and counting from the wheat plant's visual images. The architecture of the Web-SpikeSegNet consists of 2 layers. First Layer, Client-Side Interface Layer, deals with end user's requests and corresponding responses management. In contrast, the second layer, Server Side Application Layer, consists of a spike detection and counting module. The backbone of the spike detection module comprises of deep encoder-decoder network with hourglass network for spike segmentation. The Spike counting module implements the “Analyze Particle” function of imageJ to count the number of spikes. For evaluating the performance of Web-SpikeSegNet, we acquired the wheat plant's visual images, and the satisfactory segmentation performances were obtained as Type I error 0.00159, Type II error 0.0586, Accuracy 99.65%, Precision 99.59% and F ₁ score 99.65%. As spike detection and counting in wheat phenotyping are closely related to the yield, Web-SpikeSegNet is a significant step forward in the field of wheat phenotyping and will be very useful to the researchers and students working in the domain.

Identification of cropland suitability is obligatory to adapting to the increased food needs driven by population expansion, environmental contamination, and climate change. Given this, the present study was conducted to assess cereal crops’ suitability in India’s Haryana state by integrating Analytic Hierarchy Process (AHP) and geographic information system (GIS) technique. Multiple factors were considered for this study, such as rainfall, temperature, soil texture, drainage density, pH, organic carbon, electrical conductivity, and slope. The AHP technique was utilized to decide the weights of each individual parameter using experts’ opinions. The crop-suitability model was developed using the model builder module in ArcGIS 10.8, and each input parameter was reclassified as per the optimum crop-growth requirement and overlaid utilizing the reclassify tool and weighted overlay analysis. The crop suitability classes were estimated as highly suitable, S1 (6%); moderately suitable, S2 (71%); and marginally suitable, S3 (23%) for the calculated arable land for the wheat crop. Similarly, the crop suitability class of rice S2 (28%); S3 (72%), for sorghum S1 (28%); S2 (71%); S3 (1%), for maize S2 (85%); S3 (15%) and for pearl millet S1 (60%); S2 (40%) were also estimated. The study has observed that, as per the soil physico-chemical characteristics and climate, the area is moderately fertile. Therefore, agricultural production can be improved by cultivating the crop in highly and moderately suitable zones. Diversification of marginally suitable regions for crops other than that for which it is not suitable can be taken up, which will also ensure the income security of marginal farmers.

Land suitability analysis for crops is a pre-requisite for optimum utilization of the available resources and sustainable agricultural production. The present study proposes a framework for crop suitability estimation using 13 agricultural crops in Bundelkhand region using attributes like soil, climate, topography, socio-economic factors and infrastructural facilities. In proposed framework, all attributes and parameters were standardised and matched with the thresholds applicable for each crop. The cropwise required thresholds levels for each suitability category for all attributes and parameters were also developed. Analytical Hierarchy Process has been used to assign weights for each criteria, combining them and reaching an overall suitability for each crop in the region. The results revealed that most of the existing crops are either moderately or marginally suitable for cultivation. Further analysis highlighted that farmers are not cultivating the crops based on suitability of biophysical and irrigation parameters (indicator of sustainability) but based on suitability of socio-economic parameters. If this trend continues, ecosystem will suffer in longer run. Thus, there is a need for creating awareness among farming community and also revising price policy so as to improve socio-economic suitability of crops in favour of biophysically suitable crops.

Wheat rust is a severe fungal disease that significantly impacts wheat crops, resulting in substantial losses in quality and quantity, often exceeding 50%. Timely and early accurate estimation of disease severity in fields is critical for effective disease management. Early identification of Rust at low severity levels can facilitate prompt implementation of control measures, potentially saving crops. This paper introduces an automated wheat rust severity stage estimation model utilizing the EfficientNet architecture and attention mechanism. The convolutional Block Attention Module was integrated into EfficientNet-B0 in place of the SE module to enhance feature extraction by simultaneously considering channel and spatial information. The proposed hybrid approach aims to identify rust disease severity accurately. The model is trained on an image dataset comprising three major rust types—stripe, stem, leaf, and healthy plants captured under real-life field conditions. Each disease is categorized into four severity stages: healthy, low, medium, and high. Experimental results demonstrate that the proposed model achieves impressive performance, with a training accuracy of 99.51% and a testing accuracy of 96.68%. Moreover, comparative analysis against state-of-the-art CNN models highlights the superior performance of our approach. An Android application was also designed and developed to facilitate real-time classification of plant disease severity. This system incorporates a severity model optimized for enhanced classification accuracy and rapid recognition, ensuring efficient performance.