Mangrove forests are important and known as one of the most productive ecosystems in the tropics. They reduce the impacts of extreme events, provide important breeding grounds for aquatic species and build the resilience of ecosystem-dependent coastal communities. On the contrary, they are also known as one of the most threatened and vulnerable ecosystems worldwide, which have experienced a dramatic decline due to extensive coastal development during the last half-century. Remote sensing techniques have demonstrated a high potential to detect, identify, map, and monitor mangrove conditions and its changes, which is reflected by a large number of scientific papers published on this topic. The aim of this study was to investigate the multi-decadal changes of mangrove forests selected communes in Hai Phong city, North Vietnam, based on using Landsat and Sentinel 2 data from 2000 to 2018. The study used these continuous steps: 1) data pre-processing; 2) image classification using Normalized Difference Vegetation Index; 3) accuracy assessments; and 4) multi-temporal change detection and spatial analysis of mangrove forests. The classification maps in comparison with the ground reference data showed the satisfactory agreement with the overall accuracy was higher than 80.0%. From 2000 to 2018, the areas of mangrove forests in the study regions  increased by 584.2 ha in Dai Hop and Bang La communes (Region 1) and by 124.2 ha in Tan Thanh, Ngoc Xuyen and Ngoc Hai communes (Region 2), mainly due to the boom of mangrove planting projects and good mangrove management at the local community level.

Mangrove forests have been globally recognised as their vital functions in preventing coastal erosion, mitigating effects of wave actions and protecting coastal habitats and adjacent shoreline land-uses from extreme coastal events. However, these functions are under severe threats due to the rapid growth of population, intensive shrimp farming and the increased intensity of severe storms in Hau Loc and Nga Son districts, Thanh Hoa province. This research was conducted to monitor spatial-temporal changes in mangrove extents using Landsat and Sentinel imageries from 2005 to 2018. Unsupervised and supervised classification methods and vegetation indices were tested to select the most suitable classification method for study sites, then to quantify mangrove extents and their changes in selected years. The findings show that supervised classification was the most suitable in study sites compared to vegetation indices and unsupervised classification. Mangrove forest extents increased by 7.5 %, 38.6 %, and 47.8 % during periods of 2005 - 2010, 2010 - 2015 and 2015 - 2018, respectively. An increase of mangrove extents resulted from national programs of mangrove rehabilitation and restoration during 2005- 2018, increased by 278.0 ha (123.0 %).

The results of this preliminary study indicate that 29.1 percent of all car drivers and motorcycle riders presenting at hospitals with RTIs exceeded the legal BAC limit for operating a motor vehicle. Though further study is required, this is suggestive that strengthening the enforcement of drink-driving laws is an urgent national road safety priority.

Background Interpreting point-of-care lung ultrasound (LUS) images from intensive care unit (ICU) patients can be challenging, especially in low- and middle- income countries (LMICs) where there is limited training available. Despite recent advances in the use of Artificial Intelligence (AI) to automate many ultrasound imaging analysis tasks, no AI-enabled LUS solutions have been proven to be clinically useful in ICUs, and specifically in LMICs. Therefore, we developed an AI solution that assists LUS practitioners and assessed its usefulness in  a low resource ICU. Methods This was a three-phase prospective study. In the first phase, the performance of four different clinical user groups in interpreting LUS clips was assessed. In the second phase, the performance of 57 non-expert clinicians with and without the aid of a bespoke AI tool for LUS interpretation was assessed in retrospective offline clips. In the third phase, we conducted a prospective study in the ICU where 14 clinicians were asked to carry out LUS examinations in 7 patients with and without our AI tool and we interviewed the clinicians regarding the usability of the AI tool. Results The average accuracy of beginners’ LUS interpretation was 68.7% [95% CI 66.8–70.7%] compared to 72.2% [95% CI 70.0–75.6%] in intermediate, and 73.4% [95% CI 62.2–87.8%] in advanced users. Experts had an average accuracy of 95.0% [95% CI 88.2–100.0%], which was significantly better than beginners, intermediate and advanced users (p < 0.001). When supported by our AI tool for interpreting retrospectively acquired clips, the non-expert clinicians improved their performance from an average of 68.9% [95% CI 65.6–73.9%] to 82.9% [95% CI 79.1–86.7%], (p < 0.001). In prospective real-time testing, non-expert clinicians improved their baseline performance from 68.1% [95% CI 57.9–78.2%] to 93.4% [95% CI 89.0–97.8%], (p < 0.001) when using our AI tool. The time-to-interpret clips improved from a median of 12.1 s (IQR 8.5–20.6) to 5.0 s (IQR 3.5–8.8), (p < 0.001) and clinicians’ median confidence level improved from 3 out of 4 to 4 out of 4 when using our AI tool. Conclusions AI-assisted LUS can help non-expert clinicians in an LMIC ICU improve their performance in interpreting LUS features more accurately, more quickly and more confidently.