LEIFMCY: Deployment of an Efficient Low-Cost & Energy-Aware Multiparametric IoT-Based Fertilization and Irrigation Monitoring Model for Cotton Yield Analysis
Keywords:
Soil Analysis, IoT-based Model, Ensemble Learning, Yield Prediction, Energy EfficiencyAbstract
With the increasing demands on global agriculture, there is an imperative need to optimize crop yields and promote sustainable agricultural practices. Real-time monitoring and accurate predictions of soil health and crop yields have significant implications for farmers, agronomists, and policymakers. While existing soil analysis models offer certain predictive capabilities, their efficiency is often hindered by issues related to energy consumption, prediction delay, and accuracy levels. Contemporary soil models primarily fall short in addressing the multifaceted nature of soil attributes and their dynamic interactions. These models also struggle to provide real-time insights, frequently leading to delayed interventions, misallocated resources, and suboptimal yields. In this paper, we introduce an advanced, low-cost, and energy-aware multiparametric IoT-based soil analysis model designed to overcome the prevailing limitations. Our system harnesses the synergy of N, P, K, Humidity, and Temperature sensors, augmented with temporal datasets to offer a comprehensive view of the soil's current state. At the core of our analysis, an ensemble learning model combines the strengths of Naive Bayes, Logistic Regression, SVM, MLP, and 1D CNN methods, streamlining accurate yield level predictions. To further refine the model's efficiency, a Q Learning approach is integrated, ensuring both energy conservation and heightened prediction accuracy. When deployed in various agronomic scenarios, the proposed model manifested a marked improvement in prediction metrics. Notably, we observed a 10.5% enhancement in precision, 9.4% in accuracy, 8.5% in recall, and 4.5% in AUC. Moreover, the model reduced the prediction delay by 9.5% compared to its counterparts. These advancements underscore the potential of our model to revolutionize soil analysis techniques, paving the way for smarter, energy-efficient, and productive agricultural practices.
Downloads
References
Iniyan, S., Jebakumar, R. Mutual Information Feature Selection (MIFS) Based Crop Yield Prediction on Corn and Soybean Crops Using Multilayer Stacked Ensemble Regression (MSER). Wireless Pers Commun 126, 1935–1964 (2022). https://doi.org/10.1007/s11277-021-08712-9
Jain, K., Choudhary, N. Comparative analysis of machine learning techniques for predicting production capability of crop yield. Int J Syst Assur Eng Manag 13 (Suppl 1), 583–593 (2022). https://doi.org/10.1007/s13198-021-01543-8
Bali, N., Singla, A. Emerging Trends in Machine Learning to Predict Crop Yield and Study Its Influential Factors: A Survey. Arch Computat Methods Eng 29, 95–112 (2022). https://doi.org/10.1007/s11831-021-09569-8
Naz, S., Uroos, M. Synthesis of 5-Ethoxymethylfurfural (5-EMF) from Sugars and Lignocellulosic Crop Residue Using Ionic Liquids Differing in Their Cationic Structure. Waste Biomass Valor 14, 2225–2236 (2023). https://doi.org/10.1007/s12649-022-02010-6
Custodio, J.M., Billones, R.K., Concepcion, R. et al. Optimization of Crop Harvesting Schedules and Land Allocation Through Linear Programming. Process Integr Optim Sustain (2023). https://doi.org/10.1007/s41660-023-00357-4
Gupta, A., Nahar, P. Classification and yield prediction in smart agriculture system using IoT. J Ambient Intell Human Comput 14, 10235–10244 (2023). https://doi.org/10.1007/s12652-021-03685-w
Saritha, S., Thangaraja, G.A. Prediction of crop disease using Rank Regressive Learning and Proaftn Fuzzy Classification models. Soft Comput (2023). https://doi.org/10.1007/s00500-023-08357-9
Vaidhehi, M., Malathy, C. Design of GRT feature approximation-based segmentation and DCNN weed classification for effective yield estimation and fertilizer regulation. Soft Comput 27, 5021–5040 (2023). https://doi.org/10.1007/s00500-023-08005-2
Poonia, R.C., Bhatnagar, V. Design of decision support system to identify crop water need. J Ambient Intell Human Comput 14, 5171–5178 (2023). https://doi.org/10.1007/s12652-021-03291-w
Sanghavi, V.B., Bhadka, H. & Dubey, V. Hunger games search based deep convolutional neural network for crop pest identification and classification with transfer learning. Evolving Systems 14, 649–671 (2023). https://doi.org/10.1007/s12530-022-09449-x
Jain, S., Dharavath, R. Memetic salp swarm optimization algorithm based feature selection approach for crop disease detection system. J Ambient Intell Human Comput 14, 1817–1835 (2023). https://doi.org/10.1007/s12652-021-03406-3
Torres-Tello, J., Ko, SB. Interpretability of artificial intelligence models that use data fusion to predict yield in aeroponics. J Ambient Intell Human Comput 14, 3331–3342 (2023). https://doi.org/10.1007/s12652-021-03470-9
Arun Kumar, K., Karthikeyan, J. Review on implementation of IoT for environmental condition monitoring in the agriculture sector. J Ambient Intell Human Comput 13, 183–200 (2022). https://doi.org/10.1007/s12652-021-03605-y
Meivel, S., Maheswari, S. Monitoring of potato crops based on multispectral image feature extraction with vegetation indices. Multidim Syst Sign Process 33, 683–709 (2022). https://doi.org/10.1007/s11045-021-00809-5
Meenakshi, M., Naresh, R. Machine learning based classifying polluted soil health and productivity analysis in Tamil Nadu delta area in water management system. Soft Comput (2023). https://doi.org/10.1007/s00500-023-08237-2
Dayana, D.S., Kalpana, G. & Vigneswaran, T. Implementation of circular blockchain-based approach for food crops supply chain with bitcoin prediction using deep learning. Soft Comput (2023). https://doi.org/10.1007/s00500-023-08484-3
Pang, D., Wang, H., Ma, J. et al. DCTN: a dense parallel network combining CNN and transformer for identifying plant disease in field. Soft Comput 27, 15549–15561 (2023). https://doi.org/10.1007/s00500-023-09071-2
Mishra, R., Kavita, Rajpal, A. et al. I-LDD: an interpretable leaf disease detector. Soft Comput (2023). https://doi.org/10.1007/s00500-023-08512-2
Niu, H., Zhao, T., Wang, D. et al. Estimating Evapotranspiration of Pomegranate Trees Using Stochastic Configuration Networks (SCN) and UAV Multispectral Imagery. J Intell Robot Syst 104, 66 (2022). https://doi.org/10.1007/s10846-022-01588-2
Kurmi, Y., Saxena, P., Kirar, B.S. et al. Deep CNN model for crops’ diseases detection using leaf images. Multidim Syst Sign Process 33, 981–1000 (2022). https://doi.org/10.1007/s11045-022-00820-4
Chen, J., Zeb, A., Nanehkaran, Y.A. et al. Stacking ensemble model of deep learning for plant disease recognition. J Ambient Intell Human Comput 14, 12359–12372 (2023). https://doi.org/10.1007/s12652-022-04334-6
Zeng, C., Zhang, F. & Luo, M. A deep neural network-based decision support system for intelligent geospatial data analysis in intelligent agriculture system. Soft Comput 26, 10813–10826 (2022). https://doi.org/10.1007/s00500-022-07018-7
Kaur, P., Harnal, S., Gautam, V. et al. A novel transfer deep learning method for detection and classification of plant leaf disease. J Ambient Intell Human Comput 14, 12407–12424 (2023). https://doi.org/10.1007/s12652-022-04331-9
K., K., Rajpal, N., Yadav, J. et al. Multi-resolution analysis and deep neural network architecture based hybrid feature extraction technique for plant disease identification and severity estimation. Evol. Intel. (2022). https://doi.org/10.1007/s12065-022-00800-4
Rezk, N.G., Attia, AF., El-Rashidy, M.A. et al. An Efficient Plant Disease Recognition System Using Hybrid Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs) for Smart IoT Applications in Agriculture. Int J Comput Intell Syst 15, 65 (2022). https://doi.org/10.1007/s44196-022-00129-x
Kumar, S.A.S., Naveen, R., Dhabliya, D., Shankar, B.M., Rajesh, B.N. Electronic currency note sterilizer machine (2020) Materials Today: Proceedings, 37 (Part 2), pp. 1442-1444.
Dhabliya, D., Parvez, A. Protocol and its benefits for secure shell (2019) International Journal of Control and Automation, 12 (6 Special Issue), pp. 19-23.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
