Skripsi
ANALISIS PEMANFAATAN SATELLITE DERIVED BATHYMETRY CITRA SENTINEL-2A MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR DAN RANDOM FOREST UNTUK EKSTRAKSI KEDALAMAN PERAIRAN DANGKAL DI TAMAN NASIONAL KARIMUNJAWA
The Satellite Derived Bathymetry (SDB) method can collect bathymetry data in shallow waters based on satellite imagery. The bathymetry data obtained from this methos can be used to fill in the gaps in data collected from hydrographic surveys. The purpose of this research is to evaluate the use of two algorithms in obtaining information on the depth of shallow waters in Karimunjawa waters. The algorithm models used are K-Nearest Neighbor (KNN) and Random Forest (RF). These two algorithm models, integrate Sentinel-2A imagery data with in-situ sounding data at Karimunjawa Harbour, Alang Beach, and Bobby Beach. Based on three sounding locations, the results of this study shows that the use of KNN, produces better RMSE values in the range of 0,257 – 0,340 meters, while RF produces RMSE values in the range of 0,265 – 0,345 meters. Besides the positive about producing a better RMSE value than RF, KNN also produces a better depth profile. A good depth profile is if it shows a stable bathymetry contours and depth values. Both algorithms can detect depth well. The furthest depth that can be detected by KNN algorithm is 17,85 meters, while the use of RF can reach a depth of 17,95 meters. Both of these algorithm models depend on the number and width of the depth range of sounding data acquired.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307002244 | T110596 | T1105962023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available