In recent years, seagrass beds in Cam Ranh Bay and Thuy Trieu Lagoon have declined from 800 to 550 hectares, resulting insignificantly reducing the number of fish catch. This phenomenon is due to the effect of the degradation of water environment. Turbidity is one of the most important water quality parameters directly related to underwater light penetration which affects the primary productivity. This study aims to investigate spatiotemporal variation of turbidity in the waters with major factors affecting its patterns using remote sensing data. An algorithm for turbidity retrieval was developed based on the correlation between in situ measurements and a red band of Landsat 8 OLI with R² = 0.84 (p < 0.05). Simulating WAves Nearshore (SWAN) model was used to compute bed shear stress, a major factor affecting turbidity in shallow waters. In addition, the relationships between turbidity and rainfall, and bed shear stress induced by wind were analyzed. It was found that: (1) In the dry season, turbidity was low at the middle of the bay while it was high in shallow waters nearby coastlines. Resuspension of bed sediment was a major factor controlling turbidity during time with no rainfall. (2) In the rainy season or for a short time after rainfall in the dry season, turbidity was high due to a large amount of runoff entering into the study area.

In this study, we examined the natural recovery of mangroves in abandoned shrimp ponds located in the Wunbaik Mangrove Forest (WMF) in Myanmar using artificial neural network (ANN) classification and a change detection approach with Sentinel-2 satellite images. In 2020, we conducted various experiments related to mangrove classification by tuning input features and hyper-parameters. The selected ANN model was used with a transfer learning approach to predict the mangrove distribution in 2015. Changes were detected using classification results from 2015 and 2020. Naturally recovering mangroves were identified by extracting the change detection results of three abandoned shrimp ponds selected during field investigation. The proposed method yielded an overall accuracy of 95.98%, a kappa coefficient of 0.92, mangrove and non-mangrove precisions of 0.95 and 0.98, respectively, recalls of 0.96, and F1 scores of 0.96 for the 2020 classification. For the 2015 prediction, transfer learning improved model performance, resulting in an overall accuracy of 97.20%, a kappa coefficient of 0.94, mangrove and non-mangrove precisions of 0.98 and 0.96, respectively, recalls of 0.98 and 0.97, and F1 scores of 0.96. The change detection results showed that mangrove forests in the WMF slightly decreased between 2015 and 2020. Naturally recovering mangroves were detected at approximately 50% of each abandoned site within a short abandonment period. This study demonstrates that the ANN method using Sentinel-2 imagery and topographic and canopy height data can produce reliable results for mangrove classification. The natural recovery of mangroves presents a valuable opportunity for mangrove rehabilitation at human-disturbed sites in the WMF.