CENTRAL GOVERNMENT PROJECTS using AI (Artificial Intelligence)

Software Skills Usage: Data Science, AI, ML, DL, NLP, BERT, HFT, Python. Statistical Apps, R Studio Project Implementation Mode: Project Management, SDLC Requirements Gathering, Design, Coding and Development, STLC Testing, Weekly Status Meeting, Seminars, Value Added Courses, Industrial Projects Workshop, Internship - MoU Signed, Certificates Provided

• SHOBHIT University, New Delhi, India
• ICAR / NIRCA - Vedasandur, DINDIGUL District - Cultivation to Harvest - Crops
• ARUDECS - Bodinayakkanur, THENI District, AGAMALAI TRIBALS FARMING PROJECTS
• KVK CENDECT - Kamatchipuram, Chinnamanur, THENI District - Cultivation to Harvest - Food Products
• VIDIYAL - Rasingapuram, Bodinayakkanur, THENI District, Livestock Animal Husbandry, Cattle, Goat, Poultry, Fisheries
• KAMADENU - Chinnamanur, THENI District - Food Products
• TNAU Horticulture, Floriculture
• -- Periyakulam, THENI District - Plants, Vegetables and Fruits
• -- VELLAGAVI TRIBALS FARMING PROJECTS, DINDIGUL District

ICAR NIRCA PROJECTS using AI (Artificial Intelligence)

• Chilli Plant Disease Classification - Computer Vision Project

This Project Focuses on the Identification and Classification of Diseases affecting chilli plants using advanced computer vision techniques. Leveraging Deep Learning and Image Processing, the system analyzes leaf images to detect common Chilli Plant Diseases such as Leaf Curl, Anthracnose, Powdery Mildew, and Healthy Conditions.

• Non Destructive Evaluation of Ashwagandha Root for Estimating Secondary Metabolites using AI

This Project applies Artificial Intelligence (AI) Techniques for the non destructive analysis of ashwagandha (Withania Somnifera) roots to estimate the concentration of key secondary metabolites such as Alkaloids. Traditional Methods of analyzing metabolite content are destructive, time consuming and costly. This AI driven approach leverages spectral imaging and machine learning to offer a faster, eco-friendly and scalable alternative.

• Non Destructive Evaluation of Ashwagandha Powder for Estimating Secondary Metabolites using AI

This Project Utilizes Artificial Intelligence (AI) and Spectral Analysis Techniques to perform non-destructive evaluation of Ashwagandha (Withania Somnifera) Powder for Estimating the levels of secondary metabolites primary alkaloids, withanolides and saponins. This approach replaces traditional destructive testing (e.g. HPLC) with a faster, Cost effective and scalable AI driven model, Make it ideal for quality control in herbal and ayurvedic industries

• Ashwagandha Yield Prediction with Phenotypic Factors using AI

This Project Focuses on Predicting the Yield of Ashwagandha (Withania Somnifera) based on Phenotypic Traits using Artificial Intelligence. The aim is to assist farmers, agronomists and herbal product companies in optimizing cultivation practices and forecasting production using data driven insights . By Correlating Observable plant characteristics with root yield, the project enables proactive decisions making in agriculture.

• Chilli Yield Prediction with Phenotypic Factors using AI

This Project Leverages Artificial Intelligence to Predict the Yield of Chilli Crops based on Phenotypic Factors and Environmental Conditions. The Goal is to Support Precision Agriculture by enabling data driven decision making for farmers, agronomists, and agricultural planners. By Analyzing Measurable Plant Features, The Model Forecasting Yield Outcomes with High Accuracy.

• Castor Yield Prediction with Phenotypic Factors using AI

This Project Applied Artificial Intelligence (AI) to predict castor crop yield based on phenotypic characteristics and environmental factors. The Objective is to support castor growers and agribusiness stakeholders with accurate, data driven yield forecasting tools, enabling optimized resource use and better crop planning.

• Turmeric Yield Prediction with Phenotypic Factors using AI

This Project Harnesses the Power of Artificial Intelligence to Predict the Yield of Turmeric (Curcuma Longa) based on Phenotypic Traits and Environmental Conditions. The Goal is to empower farmers, agri-researchers and processors, with accurate yield estimates to support precision farming, harvest planning, and market forecasting in the turmeric value chain

• Tobacco Yield Prediction with Phenotypic Factors using AI

This Project Utilizes Artificial Intelligence to accurately predict the yield of tobacco (Nicotiana Tabacum) using phenotypic data and environmental variables. By leveraging Machine Learning models, the system aims to optimize crop management decisions, resource utilization and production forecasting in the tobacco industry.

• Sugarcane Yield Prediction with Phenotypic Factors using AI

This Project Employs Artificial Intelligence Techniques to predict the yield of sugarcane (Saccharum Offcinarum) based on the phenotypic and agroenvironmental factors. With focus on improving precision agriculture practices, the model assists farmers, agronomists, and sugar mills in planning, resource management, and forecasting sugarcane output.

• Weather Prediction for Vedasanthur-Daily,Weekly, Monthly using AI

This Project aims to develop an AI Powered Weather Forecasting system tailored to Vedasanthur, Tamilnadu. Providing Daily, Weekly and Monthly Predictions for Key Weather Parameters such as Temperature, Rainfall, Humidity and Windspeed. The System is designed to support agriculture, disaster preparedness, and community level planning by delivering localized and timely weather insights

• Ashwagandha Price Forecasting using Artificial Intelligence (AI)

This Project Utilizes Artificial Intelligence to forecast market prices of ashwagandha (Withania Somnifera) at various time horizons (daily, weekly, monthly). Accurate Price Forecasting is critical for farmers, traders and exporters and policy makers to make informed decisions related to cultivation, storage, Procurement and Market Timing.

• Ashwagandha Sales Forecasting using Artificial Intelligence (AI)

This Project applies Artificial Intelligence Techniques to forecast sales volume of ashwagandha based products (roots, powders, capsules, extracts) across various markets and timeframes. By Predicting demand trends, the system assists Producers,Distributors, Retailers, and Export Agencies in Optimizing Inventory, Production Planning and Marketing Strategies

• Ashwagandha Demand Forecasting using Artificial Intelligence (AI)

This Project Focuses on Forecasting the market demand for ashwagandha and its derivative products using Artificial Intelligence. By leveraging historical data and external indicators, the model enables pharmaceutical companies, exporters, processors and policy makers to anticipate demand patterns and plan procurement, manufacturing, and supply chain activities more efficiently

AGAMALAI TRIBALS FARMING PROJECTS using AI (Artificial Intelligence)

• Avocado Yield Prediction based on Phenotypic characteristics using ML and DL

This Project aims to predict avocado yield using phenotypic characteristics through advanced Machine Learning and Deep Learning Models. It leverages traits like plant height, leaf area, canopy size, and fruit metrics to forecast productivity accurately. The outcome supports precision agriculture and data-driven decision making for Avocado Farmers

• Cardamom Yield Prediction based on Phenotypic characteristics using ML and DL

This project focuses on predicting cardamom yield using phenotypic characteristics through Machine Learning and Deep Learning Models. Key Traits Such as Tiller Count, Panicle Length, Leaf Area and Capsule Size are analyzed to forecast Yield Accurately. The Solution Aims to Enhance Precision Farming and imporve productivity in Cardamom Cultivation

• Coffee Yield Prediction based on Phenotypic characteristics using ML and DL

This Project aims to Predict Coffee Yield using Phenotypic Characteristics by Applying Machine Learning and Deep Learning Techniques. Traits like Plant Height, Number of Branches, Leaf Size, Berry Count, and Ripeness are used to model yield outcomes. The System Supports Precision Agriculture and Optimized Decision Making for Coffee Growers

• Jackfruit Yield Prediction based on Phenotypic characteristics using ML and DL

This Project Aims to Predict Jack Fruit Yield Using Phenotypic Characteristics Through Machine Learning and Deep Learning Models. Features Such as Trunk Girth, Canopy Spread, Leaf Size, Fruit Count, and Fruit Weight are analyzed to estimate yield accurately. The Goal is to Enhance Yield Forecasting and Support Data Driven Cultivation Practices for Jack fruit Farmers

• Pepper Yield Prediction based on Phenotypic characteristics using ML and DL

This Project Focuses on Predicting Pepper Yield Using Phenotypic Charateristics Through Machine Learning and Deep Learning approaches. Key Traits like Vine Length, Number of Spikes, Leaf Area, Spike Length, and berry size are analyzed to forecast yield accurately. The aims to support precision farming and improve productivity in pepper Cultivation