Pemodelan Spasial Kelembaban Tanah Berbasis Indeks Spektral dengan Integrasi Citra Satelit Multi-sensor
Keywords:
estimasi, kelembaban tanah, citra satelit, multi-sensor, Random ForestAbstract
Keakuratan estimasi kelembaban tanah merupakan faktor penting dalam memonitor dan manajemen sumber daya air serta mitigasi dampak lingkungan. Pengukuran kelembaban tanah secara in-situ terbatas oleh biaya dan cakupan spasial yang rendah. Karenanya, integrasi data iklim dan citra satelit menjadi alternatif yang menarik untuk meningkatkan keakuratan estimasi kelembaban tanah. Penelitian ini mengembangkan model spasial kelembaban tanah dengan menggabungkan data iklim (suhu permukaan tanah dan curah hujan) dan indeks spektral dari citra satelit multi-sensor, termasuk Landsat 8 dan Sentinel-2, serta menggunakan algoritma Random Forest untuk klasifikasi kelembaban tanah. Hasil penelitian menunjukkan bahwa pendekatan ini menghasilkan peta kelembaban tanah dengan akurasi Overall Accuracy (OA) sebesar 0.8 dan kappa 0.75 untuk Random Forest, dan akurasi OA sebesar 0.93 dan kappa 0.92 untuk Gradient Boosting. Penelitian ini menyimpulkan bahwa integrasi data iklim dan citra satelit multi-sensor secara signifikan meningkatkan akurasi prediksi kelembaban tanah, memberikan manfaat signifikan bagi perencanaan dan pengelolaan lahan.
References
S. K. Chaudhary et al., “Machine learning algorithms for soil moisture estimation using Sentinel-1: Model development and implementation,” Advances in Space Research, vol. 69, no. 4, pp. 1799–1812, Feb. 2022, doi: 10.1016/j.asr.2021.08.022.
A. Singh and K. Gaurav, “Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images,” Sci Rep, vol. 13, no. 1, Art. no. 1, Feb. 2023, doi: 10.1038/s41598-023-28939-9.
M. Aboutalebi, L. N. Allen, A. F. Torres-Rua, M. McKee, and C. Coopmans, “Estimation of soil moisture at different soil levels using machine learning techniques and unmanned aerial vehicle (UAV) multispectral imagery,” in Proceedings of SPIE - The International Society for Optical Engineering, SPIE, 2019. doi: 10.1117/12.2519743.
D. Montero, C. Aybar, M. D. Mahecha, F. Martinuzzi, M. Söchting, and S. Wieneke, “A standardized catalogue of spectral indices to advance the use of remote sensing in Earth system research,” Sci Data, vol. 10, no. 1, p. 197, Apr. 2023, doi: 10.1038/s41597-023-02096-0.
T. T. Nguyen et al., “A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm,” Science of the Total Environment, vol. 833, 2022, doi: 10.1016/j.scitotenv.2022.155066.
W. H. Alawee, L. A. Al-Haddad, A. Basem, D. J. Jasim, H. Sh. Majdi, and A. J. Sultan, “Forecasting sustainable water production in convex tubular solar stills using gradient boosting analysis,” Desalination and Water Treatment, vol. 318, p. 100344, Apr. 2024, doi: 10.1016/j.dwt.2024.100344.
N. Farmonov et al., “Effectiveness of machine learning and deep learning models at county-level soybean yield forecasting,” HunGeoBull, vol. 72, no. 4, pp. 383–398, Jan. 2024, doi: 10.15201/hungeobull.72.4.4.
D. K. Bolton, J. M. Gray, E. K. Melaas, M. Moon, L. Eklundh, and M. A. Friedl, “Continental-scale land surface phenology from harmonized Landsat 8 and Sentinel-2 imagery,” Remote Sensing of Environment, vol. 240, p. 111685, Apr. 2020, doi: 10.1016/j.rse.2020.111685.
J. Li and D. P. Roy, “A Global Analysis of Sentinel-2A, Sentinel-2B and Landsat-8 Data Revisit Intervals and Implications for Terrestrial Monitoring,” Remote Sensing, vol. 9, no. 9, Art. no. 9, Sep. 2017, doi: 10.3390/rs9090902.
X. Gao, H. Chi, J. Huang, Y. Han, Y. Li, and F. Ling, “Comparison of Cloud-Mask Algorithms and Machine-Learning Methods Using Sentinel-2 Imagery for Mapping Paddy Rice in Jianghan Plain,” Remote Sensing, vol. 16, no. 7, Art. no. 7, Jan. 2024, doi: 10.3390/rs16071305.
G. Mancino, A. Ferrara, A. Padula, and A. Nolè, “Cross-Comparison between Landsat 8 (OLI) and Landsat 7 (ETM+) Derived Vegetation Indices in a Mediterranean Environment,” Remote Sensing, vol. 12, no. 2, Art. no. 2, Jan. 2020, doi: 10.3390/rs12020291.
P. Welikhe, J. E. Quansah, S. Fall, and W. McElhenney, “Estimation of Soil Moisture Percentage Using LANDSAT-based Moisture Stress Index,” J Remote Sensing & GIS, vol. 06, no. 02, 2017, doi: 10.4172/2469-4134.1000200.
H. S. Pokhariya, D. P. Singh, and R. Prakash, “Evaluation of different machine learning algorithms for LULC classification in heterogeneous landscape by using remote sensing and GIS techniques,” Eng. Res. Express, vol. 5, no. 4, p. 045052, Dec. 2023, doi: 10.1088/2631-8695/acfa64.
F. Trevisiol, P. Mattivi, E. Mandanici, and G. Bitelli, “Cross-Sensors Comparison of Popular Vegetation Indexes From Landsat TM, ETM=, OLI, and Sentinel MSI for Time-Series Analysis Over Europe,” IEEE Trans. Geosci. Remote Sensing, vol. 62, pp. 1–16, 2024, doi: 10.1109/TGRS.2023.3343071.
J. Useya, S. Chen, and M. Murefu, “Cropland Mapping and Change Detection: Toward Zimbabwean Cropland Inventory,” IEEE Access, vol. 7, pp. 53603–53620, 2019, doi: 10.1109/ACCESS.2019.2912807.
