Peramalan Kelembaban Tanah Berbasis IoT Menggunakan Pendekatan Machine Learning dan Deep Learning

Iin Darmiyati, Fitri Oktafiani, Ain Sahara, Dawi Yanti, Ranjiv Maulana, Hamsir Hamsir, Nurjannah Nurjannah

Abstract


Kelembaban tanah merupakan parameter penting yang mempengaruhi produktivitas tanaman serta efisiensi penggunaan air dalam sistem pertanian dan perkebunan. Pengelolaan irigasi konvensional umumnya menggunakan nilai ambang batas tetap sehingga tidak mampu memprediksi perubahan kondisi kelembaban tanah di masa mendatang. Penelitian ini mengembangkan sistem peramalan kelembaban tanah berbasis Internet of Things (IoT) dengan pendekatan machine learning dan deep learning. Sensor dihubungkan dengan mikrokontroler ESP32 yang mengirimkan data secara real time ke penyimpanan cloud. Dataset yang diperoleh terdiri dari ribuan entri dan diolah menggunakan Python melalui proses pembersihan data, normalisasi serta pelatihan model. Beberapa model prediksi yang digunakan meliputi Linear Regression, Random Forest Regression, Support Vector Regression (SVR), dan Long Short-Term Memory (LSTM). Dataset dibagi menjadi data pelatihan dan data pengujian dengan rasio 80:20. Evaluasi kinerja model dilakukan menggunakan Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa model LSTM memberikan performa prediksi terbaik karena mampu menangkap pola temporal pada data deret waktu sensor IoT. Sistem ini berpotensi mendukung pengembangan irigasi cerdas untuk meningkatkan efisiensi penggunaan air dan pengelolaan perkebunan yang berkelanjutan.

Kata kunci: Kelembaban tanah; Internet of Things; Machine Learning; Deep Learning; Pertanian presisi.

Full Text:

PDF

References


Bavana, H.S. et al. (2024) “An Investigation of the Utilizations of Machine Learning Methods in Precision Agriculture,” 2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024, pp. 880–887. Available at: https://doi.org/10.1109/ICICAT62666.2024.10922951.

Dash, S. and Sharaff, A. (2024) “Empowering Soil Science: Harnessing the Potential of Deep Learning for Accurate Soil Classification,” 2024 IEEE Silchar Subsection Conference, SILCON 2024, pp. 1–6. Available at: https://doi.org/10.1109/SILCON63976.2024.10910819.

Gorji, T., Tanik, A. and Sertel, E. (2015) “Soil Salinity Prediction, Monitoring and Mapping Using Modern Technologies,” Procedia Earth and Planetary Science, 15, pp. 507–512. Available at: https://doi.org/10.1016/j.proeps.2015.08.062.

Islam, M.R. et al. (2022) “A Review on Current Technologies and Future Direction of Water Leakage Detection in Water Distribution Network,” IEEE Access, 10(August), pp. 107177–107201. Available at: https://doi.org/10.1109/ACCESS.2022.3212769.

Jasmine, J.S.L. et al. (2022) “An Innovative Approach for Leaf-based Disease Detection in Crops and Soil Analyzer using Machine Learning for Smart Agriculture,” Proceedings of International Conference on Technological Advancements in Computational Sciences, ICTACS 2022, pp. 514–519. Available at: https://doi.org/10.1109/ICTACS56270.2022.9987759.

JASMINE, K. (2014) “済無No Title No Title No Title,” Penambahan Natrium Benzoat Dan Kalium Sorbat (Antiinversi) Dan Kecepatan Pengadukan Sebagai Upaya Penghambatan Reaksi Inversi Pada Nira Tebu [Preprint].

Kumar, M., Kumar, A. and Palaparthy, V.S. (2021) “Soil Sensors-Based Prediction System for Plant Diseases Using Exploratory Data Analysis and Machine Learning,” IEEE Sensors Journal, 21(16), pp. 17455–17468. Available at: https://doi.org/10.1109/JSEN.2020.3046295.

Prabavathi, R. and Chelliah, B.J. (2022) “An Optimized Gaussian Extreme Learning Machine (GELM) for Predicting the Crop Yield using Soil Factors,” Proceedings of the 2022 International Conference on Electronic Systems and Intelligent Computing, ICESIC 2022, pp. 219–222. Available at: https://doi.org/10.1109/ICESIC53714.2022.9783578.

Raju, N.S. et al. (2024) “AI-Powered Crop Suggestion, Yield Prediction, Disease Detection, and Soil Monitoring,” 3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024 - Proceedings, pp. 1120–1124. Available at: https://doi.org/10.1109/ICACRS62842.2024.10841754.

Satheeshkumar, S.K., Paolini, C. and Sarkar, M. (2023) “Subsurface Heat stress detection in plants using machine learning regression models,” 2023 International Conference on Intelligent Computing, Communication, Networking and Services, ICCNS 2023, pp. 57–64. Available at: https://doi.org/10.1109/ICCNS58795.2023.10193174.

Shalini Patel, N. and Kumar, H.P.M. (2022) “Soil Quality Identifying and Monitoring Approach for Sugarcane Using Machine Learning Techniques,” 4th International Conference on Emerging Research in Electronics, Computer Science and Technology, ICERECT 2022, pp. 1–5. Available at: https://doi.org/10.1109/ICERECT56837.2022.10059793.

Tanna, J. et al. (2023) “Heat Pulse Probe-Based Smart Soil Moisture Detection System,” IEEE Sensors Journal, 23(11), pp. 11428–11436. Available at: https://doi.org/10.1109/JSEN.2023.3266070.

Temlioglu, E., Erer, I. and Kumlu, D. (2017) “A least mean square approach to buried object detection in ground penetrating radar,” International Geoscience and Remote Sensing Symposium (IGARSS), 2017-July, pp. 4833–4836. Available at: https://doi.org/10.1109/IGARSS.2017.8128084.




DOI: https://doi.org/10.58267/petrogas.v8i1.212

Refbacks

  • There are currently no refbacks.