Vietnam secures a place among the top countries that possess the largest mangrove areas worldwide. The mangrove forests are mainly found in the Northern, Northeast, Central and Southern Delta, providing goods to habitants, and make significant help mitigate global climate change. Despite this, mangroves are severely threatened because of extensive deforestation in Vietnam. Recent advances have utilized remotely sensed imagery to present the spatial and temporal distribution of mangroves. Nevertheless, the approach is limited by imagery availability and computing resources, and difficult to share within the community. Therefore, a shareable Web-based tool that reinforces coastal managers to monitor the changes in mangroves is needed. Recently, Google Earth Engine (GEE) is a cloud-based geospatial analysis platform, which allows users to freely exploit the availability of satellite imagery and harness their computing capacity. This research aims to use GEE to detect mangrove changes, a case study in Tien Yen district, Quang Ninh, over a period from 2010 to 2020. Four supervised classification algorithms, including Random Forest (RF), Support Vector Machine (SVM), Naïve Bayes classifier, and Classification and Regression Trees (CART) have been implemented on GEE platform to select the best algorithm to produce spatial-temporal mangrove maps, then change detection of mangroves is performed. The results showed that RF demonstrated the highest accuracy with overall accuracy and kappa values of 91.04% and 0.75 respectively. The mangrove areas statistically reported by the GEE-based platform are in line with the governmental statistic report annually, marking the capabilities of GEE in natural resource management.

Chlorophyll-a (Chl-a), a proxy for phytoplankton biomass, plays an important indicator in monitoring trophic states of inland waters. This study proposes a comprehensive framework that utilizes two convolutional neural networks (CNNs) for AC (ConvNet-AC) and Chl-a estimation (ConvNet-CHL) in the eutrophic lakes of Hanoi city (Vietnam) using Landsat-8 images. Satellite-based Chl-a retrieval algorithms have been established based on water remote sensing reflectance ($R_{rs}\left(\lambda \right)$). However, existing atmospheric correction (AC) models often struggle to efficiently extract $R_{rs}\left(\lambda \right)$ due to the complex optical properties of turbid lakes, leading to significant errors in Chl-a retrieval. In this study, a total of 45,764 $R_{rs}\left(\lambda \right)$ and 13,561 Chl-a samples are synthesized using radiative transfer AC and regional Chl-a retrieval algorithms to address the scarcity of their data. A two-stage training strategy combined with hyperparameter tuning is utilized to automatically optimize the architecture of both networks. Model validation and testing are performed using a subset of synthesized data and an in situ dataset. In the comparative analysis, numerous AC approaches, including atmospheric correction for OLI “lite”, Case-2 Regional Coast Color, Image Correction for Atmospheric Effects, Landsat-8 Surface Reflectance Code, QUick Atmospheric Correction, and Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH), and the existing regional Chl-a retrieval algorithm are implemented. Results indicate that ConvNet-AC achieves an average $R^2$ = 0.72 and RMSE = 0.0024 sr⁻¹ for $R_{rs}\left(\lambda \right)$ prediction across five spectral bands, outperforming other AC candidates. The ConvNet-CHL achieves $R^2$ = 0.73 and RMSE = 40.40 mg·m⁻³ for Chl-a estimation within a range between 50 mg·m⁻³ and 300 mg·m⁻³, representing a 43% improvement over the existing regional Chl-a retrieval algorithm with RMSE = 71.99 mg·m⁻³. Furthermore, the proposed framework successfully captures the spatial and seasonal patterns of the Chl-a concentration distributions, demonstrating the effectiveness of integrating CNN-based AC and Chl-a retrieval, offering a robust and transferable solution for monitoring inland water quality with limited ground-truth data.