Weed management is the most significant process in the agricultural applications to improve the crop productivity rate and reduce the herbicide application cost. Existing weed detection techniques does not yield better performance due to the complex background and illumination variation. Hence, there arises a need for the development of effective weed identification technique. To overcome this drawback, this paper proposes a novel Angular Texture Pattern (ATP) Extraction Method for crop and weed discrimination using curvelet transformation. In our proposed work, Adaptive Median Filter (AMF) is used for filtering the impulse noise from the image. Plant image identification is performed using green pixel extraction and K-means clustering. Wrapping based Curvelet transform is applied to the plant image. Feature extraction is performed to extract the angular texture pattern of the plant image. Particle Swarm Optimization (PSO) based Differential Evolution Feature Selection (DEFS) approach is applied to select the optimal features. Then, the selected features are learned and passed through an RVM based classifier to find out the weed. Edge detection and contouring is performed to identify the weed in the plant image. Fuzzy rule-based approach is applied to detect the low, medium and high levels of the weed patchiness. From the experimental results, it is clearly observed that the accuracy of the proposed approach is higher than the existing Support Vector Machine (SVM) based approaches. The proposed approach achieves better performance in terms of Hausdorff distance, Jaccard distance, Dice distance, accuracy, sensitivity, and specificity.
18 April 2024 in International Journal of Plant & Soil Science
Maize is identified as the “Queen of Cereals” owing to its high yield. Water scarcity is a major problem, where agriculture consumes significant freshwater. Smart Irrigation with Internet of Things technology can help farmers to maximize crop production with less water. The field experiment on sensor-based drip Irrigation and farmer practice was conducted in the research field to enhance growth, yield, and water efficiency. The experiment comprised eight treatments such as T1: IoT based Drip Irrigation at 60% depletion level, T2: IoT based Drip Irrigation at 80% depletion level, T3: Drip Irrigation at 60% PE, T4: Drip Irrigation at 80% PE, T5: Drip irrigation as Normal Practice, T6: Surface Irrigation at 60% IW/CPE ratio, T7: Surface Irrigation at 80% IW/ CPE ratio and T8: Flood irrigation as Farmer’s Practice. The proposed systems-based Drip irrigation at a 60% depletion level can be recommended for hybrid maize to augment higher grain and straw yield. The highest water saving was recorded in IoT-based Drip Irrigation at a 60% depletion level(46.88%) followed by IoT-based Drip Irrigation at an 80% depletion level(40.63%).
28 November 2022 in Legume Research - An International Journal
Background: In some of Alfisol areas of Tamil Nadu, surface crusting seems to be a major constraint in the districts namely Pudukkottai, Trichy, Thanjavur, Cuddalore and Sivagangai where Alfisols accounts for 4,51,584 ha (4.49% TGA) in which groundnut is cultivated as a major crop. However, amid the above constraint, the area under groundnut is getting declined. Methods: With an aim to overcome the above constraint, a field experiment was conducted at Agricultural College and Research Institute, Tamil Nadu Agricultural University, Kudumiyanmalai during 2016-2017 and 2017-2018 in surface crusting Alfisol to investigate the response of Groundnut to various amendments under different land configuration. The experiment was laid out in Split plot design. Result: The results of the experiment revealed that among the main plot treatments, the land configuration of raised bed (M1) has influenced the growth attributes such as plant height, LAI, dry matter production, root length, root spread besides yield during 2016-2017 and 2017-2018 and this was closely followed by ridges and furrow system. Under sub plot treatments, there was remarkable increase in all the growth parameters and yield at Bio-char @ 5 t ha-1 (S1) during 2016-2017 and 2017-2018.There was no significant effect between main and sub plots.
Agriculture contributes a major share to the Indian economy and most of its people are dependent on it for their livelihood. This makes water an important resource that must be preserved using the latest available technologies. An adequate amount of water for irrigation is needed for healthy crops and to increase productivity. Water scarcity is a major problem facing the world, where agriculture consumes a significant portion of freshwater. Many researchers have focused on developing intelligent irrigation systems using Internet of Things (IoT) technology. This paper presents an IoT-based, cost-effective intelligent water management system for smart irrigation. The developed system uses soil moisture and weather data to take intelligent decisions to automate irrigation using a cloud-, web- and mobile-based applications. The proposed system uses eight treatments with four types of irrigation methods such as IoT-based drip irrigation (60 % and 80 % depletion levels - T1 and T2); drip irrigation based on PE ratio (60 % and 80 % depletion levels - T3, T4 and normal practice T5); surface irrigation based on IW/CPE ratio (60 % and 80 % depletion levels - T6, T7) and flood irrigation (T8) are used. In all systems, water was applied at 60 % and 80 % depletion levels. This demonstrates the IoT- and cloud-based system enable precision agriculture by reducing human intervention in irrigation. The highest water saving was recorded in IoT-based drip irrigation at 60 % depletion level (46.88 %), followed by IoT-based drip irrigation at 80 % depletion level (40.63 %). Therefore, the proposed IoT-based drip irrigation system at 60 % depletion level can be recommended for hybrid maize to achieve higher grain and straw yields.
The objective of this study was to identify the most suitable linear and non-linear growth models for predicting the area, productivity, and production of gingelly in Tamil Nadu, as well as to project its future growth (until 2026 A.D.). The seasonal crop report of Tamil Nadu provided time series data regarding the area, productivity, and production of gingelly for a 58-year period spanning from 1965–1966 to 2022–2023. The study involved fitting multiple trend equations, including linear and non-linear growth models, to determine the best-fitting model for gingelly production in Tamil Nadu. For the forecasting up to 2026, the model that best suited the data was selected based on its highest coefficient of determination (R2) and lowest Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) values. During the study period, the average gingelly area, production, and productivity in Tamil Nadu were recorded as 93892 ha, 37471 t, and 431 kg/ha, respectively. The cubic model's predictions for the future showed that area, productivity, and production will all rise significantly. By 2026 A.D., the predicted area is expected to be 28338.62 hectares, while production and productivity are projected to reach 15211.87 t and 581.22 kg/ha, respectively.