[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-118642-113":3,"detail-sidebar-cat-0-id-113":81,"doc-detail-118642-id":128},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},113,"id","machine-learning-application-for-improving-bathymetry-accuracy-from-satellite-imagery","Aplikasi Machine Learning untuk Peningkatan Akurasi Batimetri dari Citra Satelit","","Pemetaan batimetri merupakan aspek penting dalam pengelolaan sumber daya kelautan, namun metode in-situ seperti survei sonar terkendala biaya serta cakupan area. Penelitian ini mengembangkan pendekatan berbasis penginderaan jauh menggunakan citra Sentinel-2A untuk meningkatkan akurasi estimasi batimetri. Model machine learning Random Forest dan Support Vector Machine digunakan untuk memprediksi kedalaman, kemudian divalidasi dengan data in-situ dan dievaluasi memakai MAE, RMSE, serta R². Random Forest menghasilkan performa terbaik (MAE 1.1704, RMSE 1.5976, R² 0.8092).",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/id/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/id/document/penelitian-laporan/","Penelitian & Laporan",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/id/document/machine-learning-application-for-improving-bathymetry-accuracy-from-satellite-imagery/118642/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/machine-learning-application-for-improving-bathymetry-accuracy-from-satellite-imagery/118642.png","ImageObject",300,407,{"name":42,"@type":43},"Aurelia","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-09-19","2026-08-02",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Algoritma machine learning apa yang digunakan untuk estimasi batimetri?","Question",{"text":63,"@type":64},"Penelitian menggunakan Random Forest (RF) dan Support Vector Machine (SVM) untuk memprediksi kedalaman berdasarkan citra.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Citra satelit apa yang dipakai dalam penelitian ini?",{"text":68,"@type":64},"Penelitian berbasis citra Sentinel-2A untuk membangun estimasi batimetri.",{"name":70,"@type":61,"acceptedAnswer":71},"Bagaimana hasil terbaik diperoleh dan metrik apa yang digunakan?",{"text":72,"@type":64},"Random Forest memberikan akurasi tertinggi dengan MAE 1.1704, RMSE 1.5976, dan R² 0.8092, yang dinilai menggunakan data in-situ dan metrik MAE, RMSE, serta R².","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},118642,1785684662,{"code":4,"msg":82,"data":83},"success",[84,89,93,97,101,105,108,112,116,120,124],{"id":85,"doc_module":4,"doc_module_name":25,"category_name":86,"show_sort_weight":87,"slug":88},55,"Agama & Spiritualitas",60,"religion-spirituality",{"id":90,"doc_module":4,"doc_module_name":25,"category_name":91,"show_sort_weight":87,"slug":92},48,"Cerita & Novel","story-novel",{"id":94,"doc_module":4,"doc_module_name":25,"category_name":95,"show_sort_weight":87,"slug":96},56,"Gaya Hidup","lifestyle",{"id":98,"doc_module":4,"doc_module_name":25,"category_name":99,"show_sort_weight":87,"slug":100},51,"Komik","comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":87,"slug":104},53,"Layanan Kesehatan","healthcare",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":87,"slug":107},54,"research-report",{"id":109,"doc_module":4,"doc_module_name":25,"category_name":110,"show_sort_weight":87,"slug":111},49,"Sastra","literature",{"id":113,"doc_module":4,"doc_module_name":25,"category_name":114,"show_sort_weight":87,"slug":115},52,"Teknologi","technology",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":118,"show_sort_weight":87,"slug":119},50,"Ujian","exam",{"id":121,"doc_module":4,"doc_module_name":25,"category_name":122,"show_sort_weight":87,"slug":123},57,"Umum","general",{"id":125,"doc_module":4,"doc_module_name":25,"category_name":126,"show_sort_weight":4,"slug":127},181,"Formulir","formulir",{"code":4,"msg":82,"data":129},{"doc_id":79,"user_id":130,"nickname":42,"user_avatar":131,"doc_module":4,"category_id":106,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":132,"file_id":133,"file_url":134,"file_type":135,"file_size":136,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":26,"language":137,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":138,"faqs":139,"seo_title":140,"seo_description":12,"update_tm":80,"read_time":30},962085564807,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","ABSTRAK  \nPemetaan batimetri merupakan aspek penting dalam pengelolaan sumber dayakelautan. Metode In-situ seperti survei sonar memiliki keterbatasan dalam hal biaya dan cakupan area, sehingga pendekatan alternatif melalui penginderaanjauh berbasis citra satelit menjadi solusi yang efisien. Penelitian ini bertujuan untuk meningkatkan akurasi estimasi batimetri menggunakan algoritma machine learning, yaitu Random Forest (RF) dan Support Vector Machine (SVM), berbasis citra Sentinel-2A. Lokasi penelitian berada di perairan Kepulauan Obi, Halmahera Selatan. Hasil prediksi kedalaman kemudian divalidasi menggunakan data in-situ dan diuji menggunakan metrik MAE, RMSE, dan R². Hasil menunjukkan bahwa algoritma Random Forest memberikan akurasi terbaikdengan nilai MAE 1.1704, RMSE 1.5976, dan R² sebesar 0.8092. Algoritma SVMjuga menunjukkan performa yang baik namun masih berada di bawah RF. Dibandingkan dengan algoritma Lyzenga, metode machine learning terbukti lebihunggul dalam menangkap hubungan non-linear antara nilai reflektansi dan kedalaman perairan. Penelitian ini membuktikan bahwa integrasi citra satelit dengan machine learning mampu meningkatkan kualitas pemetaan batimetrisecara signifikan dan efisien.  \nKata kunci: Batimetri, Machine Learning, Citra Satelit, Random Forest, Support Vector Machine  \nABSTRACT  \nBathymetric mapping is crucial for the management of marine resources. In–situ methods such as sonar surveys face limitations in cost and area coverage, making satellite remote sensing a more efficient alternative. This study aims to improve the accuracy of bathymetry estimation using machine learning algorithms, namely Random Forest (RF) and Support Vector Machine (SVM), based on Sentinel- 2A satellite imagery. The study was conducted in the waters of Obi Islands, South Halmahera. Predicted depths were validated using in-situ measurements and evaluated using MAE, RMSE, andR² metrics. The results showed that the Random Forest algorithm achieved the highest accuracy with MAE of 1.1704, RMSE of 1.5976, and R² of 0.8092. While SVM also performed well, its accuracy was slightly lower than RF. Compared to the Lyzenga algorithm, machine learning methods proved more effective in capturing non-linear relationships between reflectance values and water depth. This study demonstrates that the integration of satellite imagery with machine learning significantly enhances the efficiency and accuracy of bathymetric mapping.  \nKeywords: Bathymetry, Machine Learning, Satellite Imagery, Random Forest, Support Vector Machine","cbCaiiATsRSTsFRX","https://ap.wps.com/l/cbCaiiATsRSTsFRX","pdf",142159,"Indonesian","# Metode dan Tujuan Penelitian\n## Algoritma Machine Learning (RF dan SVM)\n## Data Citra dan Lokasi Studi\n# Validasi dan Evaluasi Model\n## Metrik MAE, RMSE, dan R²\n## Perbandingan dengan Metode Lyzenga","[{\"question\":\"Algoritma machine learning apa yang digunakan untuk estimasi batimetri?\",\"answer\":\"Penelitian menggunakan Random Forest (RF) dan Support Vector Machine (SVM) untuk memprediksi kedalaman berdasarkan citra.\"},{\"question\":\"Citra satelit apa yang dipakai dalam penelitian ini?\",\"answer\":\"Penelitian berbasis citra Sentinel-2A untuk membangun estimasi batimetri.\"},{\"question\":\"Bagaimana hasil terbaik diperoleh dan metrik apa yang digunakan?\",\"answer\":\"Random Forest memberikan akurasi tertinggi dengan MAE 1.1704, RMSE 1.5976, dan R² 0.8092, yang dinilai menggunakan data in-situ dan metrik MAE, RMSE, serta R².\"}]","Aplikasi Machine Learning untuk Peningkatan Akurasi Batimetri dari Citra Satelit | PDF"]