Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69207
Volume:
10 |
11 |
Nov 2026
Pages:
1-9
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.
Department of Computer Science
MIT-ADT University
Department of Computer Science
MIT-ADT University
Department of Computer Science
MIT-ADT University
Department of Computer Science
MIT-ADT University
Smallholder farmers may need to assess crop health with incomplete field observations, limited access to agronomic expertise, and intermittent network connectivity. Image-based plant-disease classifiers provide useful screening capabilities, but controlled-image performance does not necessarily transfer to heterogeneous field photographs. Moreover, a leaf image alone may not capture contextual variables such as crop variety, growth stage, soil conditions, recent weather, and previous farm observations. This paper presents Dharti Mitra, a reliability-centred multimodal edge–cloud framework for crop-health monitoring and precision-agriculture decision support. The proposed research method-ology combines image-derived representations with available agricultural context through mask-aware feature fusion, followed by probability calibration and selective prediction. Low-quality, uncertain, or out-of-distribution inputs are deferred for image recapture or expert review. The framework also specifies a temporal disease-risk component, a constrained recommendation interface, and an edge–cloud execution model for low-connectivity settings. A source-code audit distinguishes the existing web-application prototype from research components that still require implementation. In the inspected prototype, crop-image analysis is a colour-distribution heuristic and weather values are simulated; no trained disease model or validated performance results are available. Accordingly, this manuscript contributes a proposed architecture, formal problem specification, implementation audit, and leakage-resistant evaluation protocol rather than unverified accuracy or field-impact claims. The research questions centre on missing-modality robustness, calibrated selective prediction under field-domain shift, and the operational trade-offs of edge–cloud deployment.
KEYWORDS
This paper has specified Dharti Mitra as a reliability-centred multimodal edge–cloud framework for crop-health monitoring and agricultural decision support. The methodology defines availability-aware feature fusion, independent probability cal-ibration, explicit selective acceptance conditions, temporal risk forecasting, and constrained recommendation ranking. The source-code audit shows that the current application provides farmer workflows and data management, while image analysis remains a colour heuristic and weather data are simulated. The proposed neural and edge components therefore require implementation and empirical validation. Future work should train and evaluate image baselines, add expert-labelled contextual observations, test missing- modality handling and field-domain generalization, and benchmark on named mobile hardware under realistic connectivity conditions. A prospective field study is required before claiming changes in crop yield, pesticide use, water consumption, or farmer income.
[1] S. Wolfert, L. Ge, C. Verdouw, and M.-J. Bogaardt, “Big data in smart farming—a review,” Agricultural Systems, vol. 153, pp. 69–80, 2017, doi: 10.1016/j.agsy.2017.01.023. [2] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018, doi: 10.1016/j.compag.2018.02.016. [3] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, vol. 7, Art. no. 1419, 2016, doi: 10.3389/fpls.2016.01419. [4] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018, doi: 10.1016/j.compag.2018.01.009. [5] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, 2019, doi: 10.1016/j.compag.2018.03.032. [6] D. Singh, N. Jain, P. Jain, P. Kayal, S. Kumawat, and N. Batra, “PlantDoc: A dataset for visual plant disease detection,” in Proc. 7th ACM IKDD CoDS and 25th COMAD, 2020, pp. 249–253, doi:10.1145/3371158.3371196. [7] E. Moupojou et al., “FieldPlant: A dataset of field plant images for plant disease detection and classification with deep learning,” IEEE Access, vol. 11, pp. 35398–35410, 2023, doi: 10.1109/ACCESS.2023.3263042. [8] K. Xiang, D. Shi, and X. Zhu, “Quantifying the reliability gap in cross-domain plant disease classification: Benchmarking the limited efficacy of standard mitigation techniques under controlled-to-field shift,” Frontiers in Plant Science, vol. 17, Art. no. 1826962, 2026, doi: 10.3389/fpls.2026.1826962. [9] T. Shrivastava, A. K. Agrawal, A. Shukla, and P. Dubey, “An uncertainty-aware evaluation framework based on hierarchical vision transformers for robust cross-domain plant leaf disease classification,” Scientific Reports, vol. 16, Art. no. 24348, 2026, doi: 10.1038/s41598-026-55107-6. [10] N. Zakeeya and S. L. Sugali, “Context aware multimodal plant disease diagnosis using agro ecological metadata and explainable inference,” Discover Computing, vol. 29, Art. no. 734, 2026, doi: 10.1007/s10791-026-10536-9.
Publication Date
11/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
Total views since publication
PDF Downloads
4
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...