Optimasi Rekonstruksi Pemetaan Geologi Berdasarkan Model Gayaberat Satelit dan Data Citra Satelit Menggunakan Algoritma Machine Learning Untuk Monitoring Lingkungan Sumber Daya Panas Bumi

Putra, Dhea Pratama Novian (2024) Optimasi Rekonstruksi Pemetaan Geologi Berdasarkan Model Gayaberat Satelit dan Data Citra Satelit Menggunakan Algoritma Machine Learning Untuk Monitoring Lingkungan Sumber Daya Panas Bumi. Masters thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 6016221002-Master_Thesis.pdf] Text
6016221002-Master_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2026.

Download (51MB) | Request a copy

Abstract

Monitoring aspek spasial permukaan panas bumi menerapkan teknik rekonstruksi model batuan permukaan yang berkaitan dengan kondisi bawah permukaan bumi. Rekonstruksi model batuan permukaan penting dalam penentuan arah evaluasi pengembangan lapangan panas bumi berkelanjutan. Penelitian ini mengambil sudut pandang geosains dalam memodelkan kondisi permukaan bumi sebelum dan sesudah proses ekstraksi panas bumi dilakukan pada Lapangan Panas Bumi Patuha, Jawa Barat. Global Gravity Model Plus (GGMPlus) menjadi dasar model utama nilai densitas batuan permukaan, serta fundamental delineasi bidang patahan geologi. Distribusi densitas batuan permukaan diintegrasikan dengan interpretasi citra litologi dan land surface temperature (LST) dari pengolahan data citra satelit Landsat 8. Integrasi data dan model melalui proses rekonstruksi spasial algoritma machine learning Convolutional Neural Network (CNN) dan Random Forest (RF) untuk memberikan rekonstruksi distribusi spasial nilai fisis batuan permukaan. Multi-Criteria Decision Making (MCDM) diterapkan pada akhir pengolahan data dalam fungsinya sebagai preferensi algoritma machine learning dalam representasi rekonstruksi spasial batuan permukaan lebih baik. Dari tahun 2013 hingga 2017 terjadi penurunan nilai densitas batuan (-0,19 hingga -0,05 gr/cm3), penurunan nilai LST (-25,15 hingga -2,50 °C), serta perubahan distribusi material permukaan dari aktivitas vulkanik dan proses pelapukan menunjukkan dinamika litologi permukaan. Hasil rekonstruksi spasial fitur geologi permukaan Lapangan Panas Bumi Patuha dari tahun 2013 ke 2017 menunjukkan perubahan distribusi jenis batuan permukaan dengan preferensi algoritma CNN menghasilkan model lebih baik dibandingkan algoritma Random Forest. Hal ini memperkuat hasil perubahan citra litologi permukaan yang berhubungan dengan dinamika ekstraksi panas bumi. Perubahan sifat fisik permukaan menjelaskan penurunan daya dukung lingkungan terhadap pembangkit listrik tenaga panas bumi setelah dilakukan ekstraksi. Peningkatan dukungan lingkungan seperti pelestarian daerah resapan air tanah, pembatasan perubahan penggunaan lahan, dan penghijauan menjadi alternatif solusi konservasi energi panas bumi.
=====================================================================================================
Monitoring the geothermal surface involves using rock model reconstruction techniques related to subsurface conditions. Reconstructing rock models is crucial for assessing sustainable geothermal field development. This research uses a geoscience perspective to model the condition of the earth's surface before and after geothermal extraction at the Patuha Geothermal Field in West Java. The Global Gravity Model Plus (GGMPlus) is the primary model for determining the distribution of surface rock density values and the fundamental mapping of geological fault planes. The density distribution of surface rocks is integrated with the interpretation of lithology and land surface temperature (LST) images from Landsat 8 satellite data processing. Integration of data and models is achieved through the spatial reconstruction process utilizing Convolutional Neural Network (CNN) and Random Forest (RF) machine learning algorithms to map the spatial distribution of surface rock physical properties. Multi-Criteria Decision Making (MCDM) is used in the final data processing stage to improve the representation of reconstructed surface rock data, guiding machine learning algorithms. From 2013 to 2017, there was a decrease in rock density (-0.19 to -0.05 g/cm³) and LST (-25.15 to -2.50 °C), as well as changes in the distribution of surface materials due to volcanic activity and weathering processes from Mount Patuha, showing the dynamics of surface lithology. Spatial reconstruction at Patuha Geothermal Field from 2013 to 2017 shows changes in rock type distribution with a preference for the CNN algorithm producing a better model compared to the Random Forest algorithm. These findings support the linkage phenomenon to geothermal extraction dynamics. This change in the physical properties of the surface explains the decrease in the environmental carrying capacity of geothermal power plants following extraction. Enhancing environmental support by preserving groundwater catchment areas, limiting land use changes, and promoting reforestation can serve as alternative solutions for geothermal energy conservation.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Data Citra Satelit, Model Gayaberat Satelit, Machine Learning, Pemetaan Geologi, Rekonstruksi Spasial, Geological Mapping, Machine Learning, Satellite Gravity Model, Satellite Imagery Data, Spatial Reconstruction
Subjects: G Geography. Anthropology. Recreation > G Geography (General) > G70.212 ArcGIS. Geographic information systems.
G Geography. Anthropology. Recreation > G Geography (General) > G70.217 Geospatial data
G Geography. Anthropology. Recreation > G Geography (General) > G70.5.I4 Remote sensing
G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA102.4.R44 Cartography--Remote sensing
G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA105.3 Cartography.
G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA139 Digital Elevation Model (computer program)
G Geography. Anthropology. Recreation > GB Physical geography > GB1003.2 Groundwater.
G Geography. Anthropology. Recreation > GB Physical geography > GB1197.7 Groundwater flow. Reservoirs
G Geography. Anthropology. Recreation > GB Physical geography > GB1199.5 Geothermal resources
G Geography. Anthropology. Recreation > GF Human ecology. Anthropogeography > GF78 T73 Sustainable living.
Q Science > Q Science (General) > Q180 Gravitation.
Q Science > QC Physics > QC111 Density and specific gravity
Q Science > QE Geology > QE539 Microseisms.
Q Science > QE Geology > QE599 Landslides. Rockslides
Q Science > QE Geology > QE601 Geology, Structural
Q Science > QE Geology > QE604 Deformation
T Technology > T Technology (General) > T57.5 Data Processing
T Technology > T Technology (General) > T58.62 Decision support systems
Divisions: Faculty of Civil Engineering and Planning > Geomatics Engineering > 29101-(S2) Master Thesis
Depositing User: Dhea Pratama Novian Putra
Date Deposited: 31 Jul 2024 05:07
Last Modified: 31 Jul 2024 05:07
URI: http://repository.its.ac.id/id/eprint/110304

Actions (login required)

View Item View Item