Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68748
Volume:
10 |
11 |
Nov 2026
Pages:
1-8
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.
Computer Science engineering with AIML
East West Institute of Technology
Computer Science engineering with AIML
East West Institute of Technology
Computer Science engineering with AIML
East West Institute of Technology
Computer Science engineering with AIML
East West Institute of Technology
(Assistant Professor, Department of CSE ( IoT & CyS including BCT)).
East West Institute of Technology
KRISHI-AgroMind AI combines soil classification, crop suitability scoring, user-confirmed retraining and economic estimates in a Streamlit application. Seven inputs—moisture, pH, temperature, nitrogen, phosphorus, potassium and electrical conductivity—support classification across six soil categories and ranking of 1,000 crop records. Four supervised models are compared: Random Forest, Gradient Boosting, Multi-Layer Perceptron and Support Vector Machine. The reported Random Forest baseline achieves 93.00% test accuracy and 92.80% five-fold cross-validation accuracy. A separate six-class soil classifier achieves 95.00% accuracy on 400 test instances. Retraining with 54 user-confirmed readings and synthetic baseline data produces a reported neural-network test accuracy of 96.11% and cross-validation accuracy of 95.61%. ESP32 USB serial and Google Sheets support telemetry ingestion. TreeSHAP attribution, seven-component suitability explanations and parameter checks describe recommendation behaviour, while Google Gemini supplies nutritional profiles. A pricing model estimates crop revenue and related financial measures. The system connects soil inputs with crop and economic comparisons; regional field validation and live market integration remain areas for further development.
KEYWORDS
This paper presented KRISHI-AgroMind AI, an explainable, continuously learning crop recommendation and agro-economic decision support platform. By combining a 93.00%-accurate Random Forest baseline, a 95.00%-accurate 6-class soil classifier, and a human-in-the-loop retraining pipeline that reaches 96.11% accuracy on confirmed field logs, the system delivers dependable edaphic diagnostics. Paired with dual-mode ESP32/Google Sheets sensor ingestion, TreeSHAP and 7-component suitability explanations, Gemini-powered nutritional insights, and a 1,000-crop pricing and revenue engine, KRISHI-AgroMind AI offers a practical, transparent blueprint for modern precision farming.
[1] S. Banerjee, P. Akhila, E. Elakiya, and B. Surendiran, "Cropbot: A chatbot for agriculture advancement," in Proc. Int. Conf. Signal Process., Comput., Electron., Power Telecommun. (IConSCEPT), IEEE, 2024, pp. 1–6. [2] N. Chandolikar, C. Dale, T. Koli, M. Singh, and T. Narkhede, "Agriculture assistant chatbot using artificial neural network," in Proc. Int. Conf. Adv. Comput. Technol. Appl. (ICACT4), IEEE, 2022, pp. 1–5. [3] V. Nivi, S. Geerthik, M. Karuppaiya, A. Muthukumaran, and S. Tamilarasan, "AgriBot: An integrated chatbot platform for precision agriculture and farmer support using deep learning techniques," in Proc. Int. Conf. Power, Energy, Control Transm. Syst. (ICPECTS), IEEE, 2024, pp. 1–6. [4] G. D. T, G. K. G, and P. M. Lavanya, "AgroMind AI: A voice-enabled agricultural advisory system using advanced natural language processing," Sathyabama Institute of Science and Technology, Tech. Rep., 2025. [5] S. Pudumalar, E. Ramanujam, R. H. Rajashree, C. Kavya, T. Kiruthika, and J. Nisha, "Crop recommendation system for precision agriculture," in Proc. 8th Int. Conf. Adv. Comput. (ICoAC), IEEE, 2017, pp. 32–36. [6] S. Parween, A. Pal, I. Snigdh, and V. Kumar, "An IoT and machine learning-based crop prediction system for precision agriculture," in Emerging Technologies for Smart Cities, Springer, 2021, pp. 9–16. [7] O. Turgut, I. Kok, and S. Ozdemir, "AgroXAI: Explainable AI-driven crop recommendation system for Agriculture 4.0," arXiv preprint, Dec. 2024. [8] E. Elbasi et al., "Crop prediction model using machine learning algorithms," Applied Sciences, vol. 13, no. 16, p. 9288, 2023. [9] "A unified stacking ensemble framework for crop recommendation and yield prediction," IEEE Xplore, 2026. [10] "Comparative analysis of machine learning algorithms for crop recommendation systems," IEEE Xplore, 2026.
Publication Date
11/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
15
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...