Ongoing Project
Development of cyber-physical system to optimize the use of grazing lands by providing accurate biomass estimates
Grazing lands cover most of the world's agricultural lands and play a crucial role in supplying feed for ruminant animals, carbon sequestration, and other ecosystem services. However, monitoring plant growth and estimating forage biomass is a complex and time-consuming task for land managers. The project I am working on combines machine learning, proximal and remote sensing, weather information, and other variables to better predict pasture biomass. While remote sensing data are useful for scaling biomass predictions, models relying solely on them often have high error levels, making predictions of dubious value to grazing land managers. My current project seeks to transform the management of grazing lands by providing the key data for better decisions and overcoming the barriers that prevent managers from adopting more effective management practices, with the final objective of allowing accurate biomass estimation. By integrating different technologies and data sources, I aim to provide an accessible and user-friendly tool that can assist land managers in improving their grazing land management practices, ultimately leading to better environmental and economic outcomes.
Completed Projects
Precision Agriculture Model to Increase Crop Productivity in India using Big Data
Sponsored by: Department of Science and Technology, Government of India
The core objective of this project is to develop a suitable prediction model to predict the weather condition and crop diseases using soil condition and environmental variables with Big Data in the geographical location of India. To create an effective and connected national smart agriculture system that enables smart decision making in agriculture management in India and ensures national alignment for implementation. The aim of developing models to predict with high impact but not to simply explain the relationship between the soil and environmental parameters. Therefore, co-linearity between present variables and past variables are included in a final model. With the crop disease prediction, the farmer could use it to make economic decisions aboutdisease treatments for control. The model recommendation is made about whether disease treatment is necessary or not. Weather forecasting with Big Data with the consideration of soil condition is the new approach which can lead to smart decision making based on environmental data. These kind of prediction models are useful in decision-making system where agriculture system is not well managed.
IoT based Decision Support System for Efficient Irrigation in Agriculture
Sponsored by: Agro glean system (AGS), Enterprise, India
Irrigation is an essential agricultural practice for food, pasture, and fiber production in semiarid and arid areas. In many countries, including India, efficient water use and management are today’s major concerns. The bulk of the irrigation water is sourced from rivers and dams and conveyed via open channels or pipelines to irrigated farms for storage before use or direct application to root zones. Irrigators who use groundwater often have storage tanks on their properties. Globally, it is estimated that about 70% of freshwater abstracted is used to irrigate 25% of the world’s croplands (399 million ha) which supply 45% of global food. Water used for industrial and domestic purposes accounts for approximately 20% and 10% of the total global water usage, respectively. The demand for freshwater resources is on the increase. The trend is likely to continue with the increasing population that comes with increased demand for food and fiber and the predicted negative impacts of climate change. There is also increased awareness of the need to provide sufficient water to serve other ecological services. There appears to be a consensus that irrigated agriculture, in general, is up against a future with less water. Automatic irrigation scheduling systems are highly demanded in the agricultural sector due to their ability to save water and manage deficit irrigation strategies. Elaborating on a functional and efficient automatic irrigation system is a complex task due to the high number of factors that the technician considers when optimally managing irrigation. Automatic learning systems propose an alternative to traditional irrigation management utilizing the automatic elaboration of predictions. This proposal aims to develop an automatic Smart Irrigation Decision Support System, SIDSS, to manage irrigation in agriculture. Our system will estimate the weekly irrigation needs of a plantation-based on both soil measurements and climatic variables gathered by several autonomous nodes deployed in the field. This will enable a closed- loop control scheme to adapt the decision support system to local perturbations and estimation errors.
Machine learning based agriculture advent for farmer activity development in India
Sponsored by: Agro glean system (AGS), Enterprise, India
There are many factors that contribute to farmers’ profitability. They are, finding effective crop hybrids, Pesticides, Air moisture, Ground Moisture, Water availability, Temperature, Rainfall, Price forecasting, Government actions and crop policies, Market prices etc. From the above mentioned attributes the proposed project plays key role: to data acquisition through developed sensors, efficient storage of data, data processing, developing efficient models using machine learning algorithms, GUI development for efficient visualization of processed data and to indicate use about the action to be taken, development of farmer friendly models. By using Big Data framework the huge volume, variety and veracity can be handled and high computational Machine Learning algorithms can be developed. By providing a GUI based system end user can be benefited.