Characterising the distribution of mangroves along the southern coast of Vietnam using multi-spectral indices and a deep learning model.

Mangroves are an ecologically and economically valuable ecosystem that provides a range of ecological services, including habitat for a diverse range of plant and animal species, protection of coastlines from erosion and storms, carbon sequestration, and improvement of water quality. Despite their significant ecological role, in many areas, including in Vietnam, large scale losses have occurred, although restoration efforts have been underway. Understanding the scale of the loss and the efficacy of restoration requires high resolution temporal monitoring of mangrove cover on large scales. We have produced a time series of 10-m-resolution mangrove cover maps using the Multispectral Instrument on the Sentinel 2 satellites and with this tool measured the changes in mangrove distribution on the Vietnamese Southern Coast (VSC). We extracted the annual mangrove cover ranging from 2016 to 2023 using a deep learning model with a U-Net architecture based on 17 spectral indices. Additionally, a comparison of misclassification by the model with global products was conducted, indicating that the U-Net architecture demonstrated superior performance when compared to experiments including multispectral bands of Sentinel-2 and time-series of Sentinel-1 data, as shown by the highest performing spectral indices. The generated performance metrics, including overall accuracy, precision, recall, and F1-score were above 90 % for entire years. Water indices were investigated as the most important variables for mangrove extraction. Our study revealed some misclassifications by global products such as World Cover and Global Mangrove Watch and highlighted the significance of our study for local analysis. While we did observe a loss of 34,778 ha (42.2 %) of mangrove area in the region, 47,688 ha (57.8 %) of new mangrove area appeared, resulting in a net gain of 12,910 ha (15.65 %) over the eight-year period of the study. The majority of new mangrove areas were concentrated in Ca Mau peninsulas and within estuaries undergoing recovery programs and natural recovery processes. Mangrove loss occurred in regions where industrial development, wind farm projects, reclaimed land, and shrimp pond expansion is occurring. Our study provides a theoretical framework as well as up-to-date data for mapping and monitoring mangrove cover change that can be readily applied at other sites.

Agricultural drought in the Vietnamese Central Highlands at 1-km resolution: Monthly and annual datasets.

Drought is a complex natural hazard which can create significant impacts on society and environment. Given that this phenomenon varies across space and changes over time dependent on various factors (e.g., physical conditions and human activities), the available of spatiotemporal drought data enables a better monitoring and assessment of drought severity This study introduced the integrated multivariate drought index (iMDI) data, a new regional drought index, at 1 km spatial and monthly temporal resolutions for the Vietnamese Central Highlands over a 20-years period. The iMDI was developed recently which is a combination of vegetation condition index (VCI), the temperature condition index (TCI), and the evaporative stress index (ESI) based on the feature of scaling algorithms (i.e., normalisations and standardisation). The data were processed using the median values of MODIS time-series imagery obtained from the Google Earth Engine (GEE) platform. The iMDI datasets are available for monthly and annual drought monitoring between 2001 and 2020. Additionally, the datasets of VCI, TCI, and ESI were provided so that users can apply for their own purposes even though these data can directly obtain from GEE or other sources. Users, especially those without technical expertise, can reap the advantages of having open access to iDMI data. By doing so, they can reduce their expenses and the time required to process data. As such, this accessibility can promote the use of data for diverse applications, such as evaluating the impact of droughts on the environment and human activities and monitoring droughts regionally.

Characterizing the spatial distribution of coral reefs in the South-Central Coast region of Viet Nam using Planetscope imagery.

This study aims to understand the spatial distribution of coral reefs in the central region of Viet Nam. We classified live coral cover in Son Tra Peninsula (ST) and Cu Lao Cham Island (CLC) in the South-Central Coast Region of Viet Nam using the Maximum Likelihood Classifier on 3 m Planetscope imagery. Confusion matrices and the accuracy of the classifier were assessed using field data (1,543 and 1,560 photographs in ST and CLC, respectively). The results showed that the reef's width ranged from 30 to 300 m across the study site, and we were able to detect live coral cover across a depth gradient of 2 to 6 m below the sea surface. The overall accuracies of the classifier (the Kappa coefficient) were 76.78% (0.76) and 78.08% (0.78) for ST and CLC, respectively. We found that 60.25% of coral reefs in ST were unhealthy and the live coral cover was less than 50%, while 25.75% and 11.46% of those in CLC were in good and excellent conditions, respectively. This study demonstrates the feasibility of utilizing Planetscope imagery to monitor shallow coral reefs of small islands at a high spatial resolution of 3 m. The results of this study provide valuable information for coral reef protection and conservation.

Examining spatiotemporal salinity dynamics in the Mekong River Delta using Landsat time series imagery and a spatial regression approach.

Most coastal areas globally face water shortages in the dry season due to salinization and drought. The Mekong River Delta (MRD) is recognized as the "Rice Bowl" in Vietnam but the negative effects of salinization and drought have damaged rice production in recent decades. However, regional assessment of the perturbation has been lacking. A Landsat-based satellite salinity index, the Enhanced Salinity Index (ESI), was developed in this study to explore patterns of annual salinity variations in agricultural land and their relationship to drought in the MRD from 1989 to 2018. The performance of the index was superior to that of other previously published remotely sensed indices, based on correlations with field measurements of electrical conductivity (i.e. groundwater and soil EC), which can be used as a proxy for salinity. The time-series ESI was then utilized to explore the spatiotemporal dynamics of salinity in the study area using the Theil-Send median trend (TS) and Mann-Kendall significance tests (MK). In addition, temporal relationships with the Normalized Difference Water Index (NDWI) were used to investigate the relationship between drought and saline intrusion. Our results showed that freshwater and brackish areas increased inland, whereas those developed for shrimp farming may increase soil and groundwater salinity. A negative correlation between drought and salinity was also observed in surface water where fish and shrimp farming activities took place, while a positive relationship was discovered in rice and annual cropland areas. This study highlights the use of ESI as an effective parameter for modelling vegetation salinity and its relationship with cropland change. We also demonstrate the feasibility of integrating satellite imagery with spatiotemporal analyses to monitor and assess regional salinization dynamics.