Nighttime light remote sensing technologies provide methods for studying spatiotemporal changes in urban areas. In this research, we study the changes in the urban zone in Zhejiang Province based on NPP/VIIRS nighttime light data. Moreover, we propose a methodology to extract urban zones through a buffer threshold analysis method and apply the standard deviation ellipse, urban scale increment, “dual-core” primacy and urban-scale Gini index to uncover the evolution of urban dynamics in Zhejiang Province. The results show that the highest overall urban area extraction accuracy was 95.9%; the highest Kappa coefficient was 91%. The nighttime light intensity changes observed in most cities in Zhejiang Province reflected three periods: “high-speed growth” from 2012–2014, “low-speed growth” from 2014–2018 and “high-speed growth” from 2019–2020. The growth rates observed during the 2019–2020 “high-speed growth” period exceeded those of the 2012–2014 period. Over nine years, the growth rates of the total nighttime light values in all cities ranged from 40% to 319%. Third-tier cities such as Quzhou and Lishui showed significant increases. Second-tier cities, such as Jinhua, Huzhou and Taizhou, had growth rates over 100%. From 2012–2014, the development rates increased in cities in southern Zhejiang Province, such as in Wenzhou and Taizhou, thus promoting a southward shift in the center of gravity. After 2014, the development rates increased in cities in northern Zhejiang Province, such as Hangzhou, Ningbo and Jiaxing, thus promoting a northward shift in the center of gravity, with the center stabilizing in the Keqiao District-Yuecheng District of Shaoxing. According to the changes observed in the “dual-core” primacy and urban-scale Gini index results derived from 2012 to 2020, the development of cities in Zhejiang Province has become more balanced over the past nine years.

Vibrio parahaemolyticus is a prevalent pathogen responsible for foodborne diseases in coastal regions. Understanding its dynamic relationship with various meteorological and marine factors is crucial for predicting outbreaks of bacterial foodborne illnesses. This study analyzes the occurrence of V. parahaemolyticus-induced foodborne illness in Zhejiang Province, China, from 2014 to 2018, using an 8-day time unit based on the temporal characteristics of marine products. The detection rate of V. parahaemolyticus exhibited a distinct cyclical pattern, peaking during the summer months. Meteorological and marine factors showed varying lag effects on the detection of V. parahaemolyticus, with specific lag periods as follows: sunshine duration (3 weeks), air temperature (3 weeks), total precipitation (8 weeks), relative humidity (7 weeks), sea surface temperature (1 week), and sea surface salinity (8 weeks). The SARIMAX model, which incorporates both marine and climatic factors, was developed to facilitate short-term forecasts of V. parahaemolyticus detection rates in coastal cities. The model’s performance was evaluated, and the actual values consistently fell within the 95% confidence interval of the predicted values, with a mean absolute error (MAE) of 0.047, indicating high accuracy. This framework provides both theoretical and practical insights for predicting and preventing future foodborne disease outbreaks. These findings can support food industry stakeholders—such as seafood suppliers, restaurants, regulatory agencies, and healthcare institutions—in anticipating high-risk periods and implementing targeted measures. These include enhancing cold chain management, conducting timely seafood inspections, strengthening cross-contamination controls during seafood processing, dynamically adjusting market surveillance intensity, and improving hygiene practices. In addition, hospitals and local health departments can use the model’s forecasts to allocate medical resources such as beds, medications, and staff in advance to better prepare for seasonal surges in foodborne illness.

As coastal tidal flats—ecosystems of high ecological significance and socio-economic value—face accelerating degradation driven by climate change and intensified anthropogenic disturbances, there is an urgent need for efficient, automated, and scalable monitoring solutions. Traditional monitoring approaches are constrained by high implementation costs and limited spatial coverage, whereas remote sensing—particularly multispectral satellite imagery such as Sentinel-2—has emerged as a primary and widely adopted tool for large-scale environmental observation. Building upon recent advancements in cloud computing and WebGIS technologies, this study presents a web-based, interactive tidal flat extraction system implemented on Alibaba’s AI Earth platform. The system integrates multiple water indices (NDWI, mNDWI, and IWI) with a machine learning algorithm (Random Forest), and is deployed through a user-friendly interface developed using Vue.js and Leaflet, enabling flexible parameter configuration and real-time visualization of extraction results. Its front-end/back-end decoupled architecture enables non-programming users to conduct large-scale tidal flat mapping, thereby substantially lowering the technical barriers to coastal tidal flat monitoring and management in China.

Tidal flats, as critical transitional ecosystems between land and sea, face significant threats from climate change and human activities, necessitating accurate monitoring for conservation and management. However, publicly available tidal flat datasets exhibit substantial discrepancies due to variations in data sources, spectral indices, and classification methods. This study systematically evaluates six widely used 2020 tidal flat datasets (GTF30, GWL_FCS30, MTWM-TP, DCTF, CTF, and TFMC) across China’s coastal zone, assessing their spatial consistency, area estimation differences, and edge classification accuracy. Using a novel edge validation point set (3150 samples) derived from tide gauge stations and low-tide imagery, we demonstrate that MTWM-TP (OA = 0.85) and TFMC (OA = 0.84) achieve the highest accuracy, while DCTF and GTF30 show systematic underestimation and overestimation, respectively. Spatial agreement is strongest in Jiangsu (49.8% unanimous pixels) but weak in turbid estuaries (e.g., Zhejiang). Key methodological divergences include sensor resolution (Sentinel-2 outperforms Landsat in low-tide coverage), spectral index selection (mNDWI reduces false positives in turbid waters), and boundary constraints (high-tide masks suppress inland misclassification). We propose establishing an automated multi-source framework integrating optical (Sentinel-2, Landsat) and radar (Sentinel-1) observation data to enhance low-tide coverage, constructing region-adaptive spectral indices and improving boundary accuracy through the combination of machine learning and thresholding algorithms. This study provides a critical benchmark for dataset selection and methodological advancements in coastal remote sensing.

Tidal flats, as critical transitional ecosystems between land and sea, face significant threats from climate change and human activities, necessitating accurate monitoring for conservation and management. However, publicly available tidal flat datasets exhibit substantial discrepancies due to variations in data sources, spectral indices, and classification methods. This study systematically evaluates six widely used 2020 tidal flat datasets (GTF30, GWL_FCS30, MTWM-TP, DCTF, CTF, and TFMC) across China’s coastal zone, assessing their spatial consistency, area estimation differences, and edge classification accuracy. Using a novel edge validation point set (2,550 samples) derived from tide gauge stations and low-tide imagery, we demonstrate that MTWM-TP (OA=0.83) and TFMC (OA=0.81) achieve the highest accuracy, while DCTF and GTF30 show systematic underestimation and overestimation, respectively. Spatial agreement is strongest in Jiangsu (49.8% unanimous pixels) but weak in turbid estuaries (e.g., Zhejiang). Key methodological divergences include sensor resolution (Sentinel-2 outperforms Landsat in low-tide coverage), spectral index selection (mNDWI reduces false positives in turbid waters), and boundary constraints (high-tide masks suppress inland misclassification). We recommend integrating multi-sensor data, dynamic index selection, and optimized thresholding algorithms to improve future tidal flat mapping. This study provides a critical benchmark for dataset selection and methodological advancements in coastal remote sensing.

Accurate mapping of coastal wetland vegetation is essential for ecological conservation and blue carbon assessment, yet it remains challenging due to fragmented boundaries, spectral similarity among species, pronounced phenological variability, and limited generalization under small-sample conditions. We propose a spatio-temporal attention hybrid network (STAH-Net) for multi-source time-series classification. A 29-band feature cube is constructed from Sentinel-1 and Sentinel-2 data, integrating monthly Normalized Difference Vegetation Index (NDVI) and vertical–vertical (VV) polarization time series with static spectral and polarimetric indices. An improved U-Net backbone with dual-branch 3D convolutions extracts optical and Synthetic Aperture Radar (SAR) temporal features in parallel, incorporating a Temporal Enhancement Attention Module (TEAM) for phenological weighting, a Local Channel Attention (LCA) module for channel recalibration, and Atrous Spatial Pyramid Pooling (ASPP) for multi-scale context. An edge-weighted hybrid loss combining edge-weighted cross-entropy and Dice loss mitigates class imbalance and boundary blurring. Experiments in Hangzhou Bay, Liaohe Estuary, and Minjiang Estuary achieves overall accuracy (OA) values of 98.16%, 97.23%, and 95.76%, respectively, with a maximum Kappa of 97.49%, outperforming ConvLSTM, U-Net, SegFormer, SITSMamba, and GLMambaNet under identical settings. Ablation and visual analyses confirm the effectiveness of the proposed modules, with NDVI phenology providing primary discrimination and VV offering complementary structural information. Cross-year and cross-region tests show promising transferability, with OAs of 97.21% and 94.75% in Liaohe Estuary for 2024 and 2020, respectively, and 93.83% in Shanghai. These results demonstrate that STAH-Net provides an effective and transferable workflow for coastal wetland vegetation mapping.