Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64146
Volume:
10 |
5 |
May 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
M.TECH
Jain Deemed-to-be University
M.TECH
Jain Deemed-to-be University
India is among the world's top agricultural producers and yet the majority of its farmers are operating on fewer than five acres lack access to data driven decision support. Current crop recommendation systems rarely consider integration of live ecological information, market information, or financial feasibility assessments, all combined. This paper introduces an Advanced AI Farming System that integrates five intelligent subsystems into an end-to-end pipeline: (1) image-driven soil classification using a Convolutional Neural Network (CNN) with MobileNetV2; (2) nutrient-aware crop recommendation using a Random Forest Classifier; (3) data-driven yield prediction using a Random Forest Regressor; (4) resilient live environmental input by a weather bot; and (5) weather risk assessment and global market sentiment analysis by zero-shot NLP Transformer (facebook/bart-large-mnli). The integrated system also generates outputs such as intercropping strategies, fertilizer plans in relation to crops and soils and comparative profit estimates for domestic and export crops. The system was tested on a series of publicly available Kaggle datasets for soil imagery classification, crop recommendation and agricultural yield prediction, showing that using computer vision, ensemble learning and natural language processing can provide a much more meaningful and deployable decision support tool than any single model.
KEYWORDS
Our Advanced AI Farming System revolutionizes crop recommendation by combining five powerful AI tools into one seamless platform. We have integrated vision-based soil classification, Random Forest crop and yield predictions, fail-safe 3-tier weather tracker, and out-of-the- box NLP market analysis in a single pipeline. But this system does more than just run the numbers, it gives real, actionable advice. We convert complex machine generated data into clear farming approaches with specific intercropping blueprints, precise nutrient formulations and side-by-side domestic vs. export profit projections, safely governed by our expert agronomic override. We intend to expand our soil database to more states in India, include real time satellite NDVI data for more comprehensive soil health analysis, and develop a compact mobile app for wider accessibility. Finally, we will track real world harvests over time to continue to prove and improve the financial and agricultural accuracy of our system.
[1] Sunitha K., Tarun Kumar G., Shaikh Saifulla, SharathKumar B. S., and Venugopal M. Bhat, "Soil Analysis and Crop Recommendation using Machine Learning," International Journal for Research Trends and Innovation (IJRTI), Volume 9, Issue 1, pp. 228– 233, 2024. ISSN: 2456-3315. [2] S. Pudumalar et al., "Crop recommendation system for precision agriculture," in Proceedings of the Eighth International Conference on Applied Computing, 2016, pp. 32–36. doi: 10.1109/ICoAC.2017.7951470. [3] R. K. Rajak et al., "A Machine Learning-Based Crop Recommendation System to Maximize Crop Yield," International Journal of Engineering and Technology, vol. 4, issue 12, pp. 950– 953, December 2017. [4] A. K. M. Reddy, S. Chithra, H. M. Hemashree, and Thanu K., "Soil Classification and Crop Suggestion using Machine Learning," International Journal for Research in Applied Science and Engineering Technology, vol. 8, issue 7, pp. 1625–1628, July 2020. [5] A. Venugopal, S. Aparna, J. Mani, R. Matthew, and V. Williams, "Crop Yield Prediction using Machine Learning Algorithms," International Journal of Engineering Research and Technology, vol. 9, issue 13, pp. 87–91, August 2021. [6] "Crop Selection Method to Maximize Crop Yield Rate using Machine Learning Technique," in Proceedings of the 2015 International Conference on Smart Technology and Management for Computing, Communications, Controls, Energy, and Materials (ICSTM), pp. 138–145. doi: 10.1109/ICSTM.2015.7225403. [7] A. T. M. S. Ahamed et al., "Applying data mining techniques to predict annual yield of major crops and recommend planting different crops in different districts in Bangladesh," in Proc. 2015 IEEE/ACIS 16th Int. Conf. on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, pp. 1–6. doi: 10.1109/SNPD.2015.7176185. [8] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520. [9] Kaggle, "Soil-Type-Classification for Crops Suggestion," [Online]. Available: https://www.kaggle.com/omkargurav/soil- classification-image-data. Accessed: 2024. [10] Kaggle, "Crop Recommendation Dataset," [Online]. Available: https://www.kaggle.com/atharvaingle/crop-recommendation-dataset. Accessed: 2024.
Publication Date
5/27/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...