Water clarity mapping of global lakes using a novel hybrid deep-learning-based recurrent model with Landsat OLI images

Predicting influenza-like illness trends based on sentinel surveillance data in China from 2011 to 2019: A modelling and comparative study1

Background

Influenza is an acute respiratory infectious disease with a significant global disease burden. Additionally, the coronavirus disease 2019 pandemic and its related non-pharmaceutical interventions (NPIs) have introduced uncertainty to the spread of influenza. However, comparative studies on the performance of innovative models and approaches used for influenza prediction are limited. Therefore, this study aimed to predict the trend of influenza-like illness (ILI) in settings with diverse climate characteristics in China based on sentinel surveillance data using three approaches and evaluate and compare their predictive performance.

Methods

The generalized additive model (GAM), deep learning hybrid model based on Gate Recurrent Unit (GRU), and autoregressive moving average-generalized autoregressive conditional heteroscedasticity (ARMA-GARCH) model were established to predict the trends of ILI 1-, 2-, 3-, and 4-week-ahead in Beijing, Tianjin, Shanxi, Hubei, Chongqing, Guangdong, Hainan, and the Hong Kong Special Administrative Region in China, based on sentinel surveillance data from 2011 to 2019. Three relevant metrics, namely, Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R squared, were calculated to evaluate and compare the goodness of fit and robustness of the three models.

Results

Considering the MAPE, RMSE, and R squared values, the ARMA-GARCH model performed best, while the GRU-based deep learning hybrid model exhibited moderate performance and GAM made predictions with the least accuracy in the eight settings in China. Additionally, the models' predictive performance declined as the weeks ahead increased. Furthermore, blocked cross-validation indicated that all models were robust to changes in data and had low risks of overfitting.

Conclusions

Our study suggested that the ARMA-GARCH model exhibited the best accuracy in predicting ILI trends in China compared to the GAM and GRU-based deep learning hybrid model. Therefore, in the future, the ARMA-GARCH model may be used to predict ILI trends in public health practice across diverse climatic zones, thereby contributing to influenza control and prevention efforts.

Remote-sensing monitoring of colored dissolved organic matter in the Arctic Ocean

In the Arctic Ocean, variations in the colored dissolved organic matter (CDOM) have important value and significance. This study proposed and evaluated a novel method by combining the Google Earth Engine with a multilayer back-propagation neural network to retrieve CDOM concentration. This model performed well on the testing data and independent validation data (R2 = 0.76, RMSE = 0.37 m-1, MAPD = 35.43 %), and it was applied to Moderate Resolution Imaging Spectroradiometer (MODIS) images. The CDOM distribution in the Arctic Ocean and its main sea areas was first depicted during the ice-free period from 2002 to 2021, with average CDOM concentration in the range of 0.25 and 0.31 m-1. High CDOM concentration appeared in coastal areas affected by rivers on the Siberian side. The CDOM concentration was highly correlated with salinity (r = -0.92) and discharge (r > 0.68), while melting sea ice diluted seawater and CDOM concentration.

An optical mechanism-based deep learning approach for deriving water trophic state of China's lakes from Landsat images

Widespread eutrophication has been considered as the most serious environment problems in the world. Given the critical roles of lakes in human society and serious negative effects of water eutrophication on lake ecosystems, it is thus fundamentally important to monitor and assess water trophic status of lakes. However, a reliable model for accurately estimating the trophic state index (TSI) of lakes across a large-scale region is still lacking due to their high complexity. Here, we proposed an optical mechanism-based deep learning approach to remotely estimate TSI of lakes based on Landsat images. The approach consists of two steps: (1) determining the optical indicators of TSI and modeling the relationship between them, and (2) developing an approach for remotely deriving the determined optical indicator from Landsat images. With a large number of in situ datasets measured from lakes (2804 samples from 88 lakes) across China with various optical properties, we trained and validated three machine learning methods including deep neural network (DNN), k-nearest neighbors (KNN) and random forest (RF) to model TSI with the optical indicators and TSI and derive the determined optical indicator from Landsat images. The results showed that (1) the total absorption coefficients of optically active constituents at 440 nm (at-w(440)) performs best in characterizing TSI, and (2) DNN outperforms other models in the inversion of both TSI and at-w(440). Overall, our proposed optical mechanism-based deep learning approach demonstrated a robust and satisfactory performance in assessing TSI using Landsat images (root mean squared error (RMSE) = 5.95, mean absolute error (MAE) = 4.81). This highlights its merit as a nationally-adopted method in lake water TSI estimation, enabling the convenience of the acquisition of water eutrophic information in large scale, thereby assisting us in managing lake ecology. Therefore, we assessed water TSI of 961 lakes (>10 km2) across China using the proposed approach. The resulting at-w(440) and TSI ranged from 0.01 m-1 to 31.42 m-1 and from 6 to 96, respectively. Of all these studied lakes, 96 lakes (11.40 %) were oligotrophic, 338 lakes were mesotrophic (40.14 %), 360 lakes were eutrophic (42.76 %), and 48 were hypertrophic (5.70 %) in 2020.

Deep learning for water quality

Understanding and predicting the quality of inland waters are challenging, particularly in the context of intensifying climate extremes expected in the future. These challenges arise partly due to complex processes that regulate water quality, and arduous and expensive data collection that exacerbate the issue of data scarcity. Traditional process-based and statistical models often fall short in predicting water quality. In this Review, we posit that deep learning represents an underutilized yet promising approach that can unravel intricate structures and relationships in high-dimensional data. We demonstrate that deep learning methods can help address data scarcity by filling temporal and spatial gaps and aid in formulating and testing hypotheses via identifying influential drivers of water quality. This Review highlights the strengths and limitations of deep learning methods relative to traditional approaches, and underscores its potential as an emerging and indispensable approach in overcoming challenges and discovering new knowledge in water-quality sciences.

Dynamic monitoring and analysis of chlorophyll-a concentrations in global lakes using Sentinel-2 images in Google Earth Engine

Remote estimation of Chlorophyll-a (Chl-a) has long been used to investigate the responses of aquatic ecosystems to global climate change. High-spatiotemporal-resolution Sentinel-2 satellite images make it possible to routinely monitor and trace the spatial distributions of lake Chl-a if reliable retrieval algorithms are available. In this study, Sentinel-2 images and in-situ measured data were used to develop a Chl-a retrieval algorithm based on 13 optical water types (OWTs) with a satisfying performance (R2 = 0.74, RMSE = 0.42 mg/m3, MAE = 0.33 mg/m3, and MAPE = 55.56 %). After removing the disturbance of algal blooms and other factors, the distribution of Chl-a in 3067 of the largest global lakes (≥50 km2) was mapped using the Google Earth Engine (GEE). From 2019 to 2021, the average Chl-a concentration was 16.95 ± 5.95 mg/m3 for the largest global lakes. During the COVID-19 pandemic, global lake-averaged Chl-a concentration reached its lowest value in 2020. From the perspective of spatial distribution, lakes with low Chl-a concentrations were mainly distributed in high-latitude, high-elevation, or economically underdeveloped areas. Among all the potential influencing factors, lake surface temperature had the largest contribution to Chl-a and showed a positive correlation with Chl-a in approximately 92.39 % of the lakes. Conversely, factors such as precipitation and tree cover area around the lake were negatively correlated with Chl-a concentration in nearly 61.44 % of the lakes.

A novel chlorophyll-a retrieval model based on suspended particulate matter classification and different machine learning

Chlorophyll-a (Chla) in inland waters is one of the most significant optical parameters of aquatic ecosystem assessment, and long-term and daily Chla concentration monitoring has the potential to facilitate in early warning of algal blooms. MOD09 products have multiple observation advantages (higher temporal, spatial resolution and signal-to-noise ratio), and play an extremely important role in the remote sensing of water color. For developing a high accuracy machine learning model of remotely estimating Chla concentration in inland waters based on MOD09 products, this study proposed an assumption that the accuracy of Chla concentration retrieval will be improved after classifying water bodies into three groups by suspended particulate matter (SPM) concentration. A total of 10 commonly used machine learning models were compared and evaluated in this study, including random forest regressor (RFR), deep neural networks (DNN), extreme gradient boosting (XGBoost), and convolutional neural network (CNN). Altogether, 41 basic bands and 820 band ratios between the 41 bands were filtered by measuring their correlation with Ln(Chla) and several bands brought into different machine learning models. Results demonstrated that the construction of Chla concentration remote estimation model based on SPM classification could significantly improve the correlation between Ln(Chla) and 41 basic spectral band combinations, the correlation between Ln(Chla) and 820 band ratios, and the model verification R2 from 0.41 to 0.83. Furthermore, B3, B20, and B32 were finally selected based on correlation with SPM to classify SPM and the classification accuracy could reach 0.9. Finally, we concluded that RFR model performed best via comparing the R2, RMSE, and MAPE. By comparing the relative contribution of input bands in different groups, B3 contributed most to three groups. The model constructed in this study has promising prospects for promotion and application in other inland waters, and could provide systematic research reference for subsequent research.

A novel total phosphorus concentration retrieval method based on two-line classification in lakes and reservoirs across China

Phosphorus is widely recognized as a nutrient that restricts growth and is the primary contributor to eutrophication in 80 % of water bodies. Consequently, the Chinese government has consistently prioritized monitoring and controlling total phosphorus (TP) levels. The remote estimation of TP in lakes and reservoirs at a national scale is a challenging task due to TP being a non-optically active parameter. Currently, there is a lack of developed TP inversion models specifically designed for lakes and reservoirs in China. For solving this problem, a novel two-line classification method drawn on scatter plots based on the natural logarithm of TP (Ln(TP)) and B33/B9 was proposed and used to classify 1211 measured samples obtained from field cruises in 105 lakes and reservoirs across China from 2012 to 2022 into three categories, Class 1, Class 2, and Class 3. Results demonstrate that the proposed classification method has the ability to enhance the correlation between Ln(TP) and 43 basic potential single band and band combinations. Specifically, the correlation range improved from (-0.31,0.15) to (-0.77,0.24) in Class 1, (-0.81, 0.36) in Class 2, and (-0.74, 0.52) in Class 3. Additionally, the classification method also improved the correlation range between Ln(TP) and 820 band ratios, from (-0.32, 0.32) to (-0.83, 0.82) in Class 1, (-0.86, 0.86) in Class 2, and (-0.86, 0.86) in Class 3. These datasets were subsequently utilized as input for eXtreme Gradient Boosting (XGBoost) models. Finally, well performing XGBoost models in Class 1 (R2 = 0.76, RMSE = 0.3, MAPE = 12 %), Class 2 (R2 = 0.84, RMSE = 0.49, MAPE = 38 %), and Class 3 (R2 = 0.74, RMSE = 0.46, MAPE = 14 %) were used to map TP of 563 large lakes and reservoirs (≥20 km2) across China using MODIS images from 2005, 2010, 2015, and 2020. This study presents a novel approach for estimating non-optically active parameters through remote sensing on a national scale.

A new approach to quantify chlorophyll-a over inland water targets based on multi-source remote sensing data

Chlorophyll-a (Chl-a) concentration is a reliable indicator of phytoplankton biomass and eutrophication, especially in inland waters. Remote sensing provides a means for large-scale Chl-a estimation by linking the spectral water-leaving signal from the water surface with in situ measured Chl-a concentrations. Single-sensor images cannot meet the practical needs for long-term monitoring of Chl-a concentrations due to cloud cover and satellite operational lifetimes. However, quantifying long-term inland water Chl-a concentrations using multi-source remote sensing data remains a problem, as improper input of satellite reflectance products will affect the accuracy of Chl-a over inland waters, as well as existing models cannot meet the need for multi-source remote sensing data to retrieve high precision Chl-a. To explore these problems towards a solution, four reflectance data derived from Ocean and Land Colour Instrument (OLCI), MultiSpectral Instrument (MSI), and Operational Land Imager (OLI) were evaluated against in situ measurements of Erhai Lake. Reflectance data from these sensors were assessed to determine their consistency. Results indicate that R_rhos products (i.e., surface reflectance, a semi-atmospheric correction reflectance) that controlled for the atmospheric diffuse transmittance were highly correlated with the measured reflectance values. The in situ reflectance also confirmed the higher fidelity of satellite reflectance in the green-red band. Subsequently, a new extreme gradient boosting (XGB) model applied to multi-source remote sensing data is proposed to estimate long-term inland water Chl-a concentrations. Comparative experiments showed the XGB model with R_rhos products outperformed other solutions, providing accurate estimates for daily, monthly, and long-term trends in Erhai Lake. The XGB model was finally processed 3954 R_rhos reflectance data derived from OLCI, ENVISAT Medium Resolution Imaging Spectrometer (MERIS), MSI, and OLI sensors, mapping Chl-a concentrations in Erhai Lake over a 20-year period. This study could serve as a reference for the long-term Chl-a monitoring using multi-source remote sensing data to support inland lake management and future water quality evaluation.

Evaluating the effectiveness of coastal environmental management policies in China: The case of Bohai Sea

With marine pollution issues becoming serious and widespread, a series of coastal environmental managemental policies are being carried out worldwide, the effectiveness of which requires comprehensive evaluation. Taking the Bohai Sea (BS) of China as an example, which has been plagued by serious ecological and environmental issues for decades due to terrestrial pollution discharge, this study explored and quantified, for the first time to our best knowledge, the variability of water quality after initiating a dedicated 3-year pollution control action (Uphill Battle for Integrated Bohai Sea Management, UBIBM, 2018-2020) implemented by China's central government, with two water quality indexes of water color (Forel-Ule index, FUI) and transparency (Secchi disk depth, Z_SD, m) from satellite observations. During the UBIBM, a significant improvement in water quality was detected, characterized by a clearer and bluer BS, with Z_SD and FUI improved by 14.1% and 3.2%, respectively, compared with the baseline period (2011-2017). In addition, an abrupt drop in the long-term record (2011-2022) of the coverage area of highly turbid waters (Z_SD≤2 m or FUI≥8) was found in 2018, which coincided with the start of the UBIBM, indicating that the water quality improvement may be attributed to the pollution alleviation of the UBIBM. Independent data of land-based pollution statistics also supported this deduction. (3) Compared with the previous two pollution control actions in the first decade of 21st century, UBIBM was proved to be the most successful one in terms of the achieved highest transparency and lowest FUI during the past two decades. Reasons for the achievement and implications to future pollution control are discussed for a more sustainable and balanced improvement in the coastal environment. This research provides a valuable example that satellite remote sensing can play a vital role in the management of coastal ecosystems by providing effective evaluation of pollution control actions.

Spatiotemporal changes and influencing factors of water clarity in the Yellow Sea over the past 20 years

Water transparency is an important parameter for describing the optical properties of water. It reflects changes in marine environment and is of great significance for guiding the development and protection of marine environment. In this study, based on the algorithm proposed by Lee et al. in 2015, water transparency in the Yellow Sea from 2003 to 2022 was inverted. The results revealed that, in terms of spatial distribution, the water in western region of the Yellow Sea had relatively low transparency, whereas the water in the central and southern regions had high transparency. Regarding temporal trends, declining transparency was observed throughout most of the study period, but the trends reversed and transparency began to increase in 2017. Empirical orthogonal function analysis confirmed that water transparency was primarily influenced by the optical constituents of water. Long-term monitoring of water clarity is of significant importance for the preservation of marine ecological environments.

Classification of land use/land cover using artificial intelligence (ANN-RF)

Because deep learning has various downsides, such as complexity, expense, and the need to wait longer for results, this creates a significant incentive and impetus to invent and adopt the notion of developing machine learning because it is simple. This study intended to increase the accuracy of machine-learning approaches for land use/land cover classification using Sentinel-2A, and Landsat-8 satellites. This study aimed to implement a proposed method, neural-based with object-based, to produce a model addressed by artificial neural networks (limited parameters) with random forest (hyperparameter) called ANN_RF. This study used multispectral satellite images (Sentinel-2A and Landsat-8) and a normalized digital elevation model as input datasets for the Sana'a city map of 2016. The results showed that the accuracy of the proposed model (ANN_RF) is better than the ANN classifier with the Sentinel-2A and Landsat-8 satellites individually, which may contribute to the development of machine learning through newer researchers and specialists; it also conventionally developed traditional artificial neural networks with seven to ten layers but with access to 1,000's and millions of simulated neurons without resorting to deep learning techniques (ANN_RF).

How does lake water clarity affect lake thermal processes?

The objective of this study was to determine the effects of water clarity changes on thermal processes in Lake Poyang, the largest freshwater lake in China, using a physically based lake model embedded in the Community Land Model. A water extinction coefficient (K_d) describing water clarity and controlling radiation penetration in the lake model was used to conduct controlled simulations. Three sets of simulations were conducted for Lake Poyang over the period from 2000 to 2015: DEFAULT with the K_d = 0.45 m⁻¹; CTL with the K_d = 1.68 m⁻¹ based on a water clarity of 0.85 m; and DARK with the K_d = 1.68 m⁻¹ from 2000 to 2005 and K_d = 3.44 m⁻¹ based on a water clarity of 0.41 m observed from 2005 to 2015. The simulation results showed that compared with the DEFAULT simulation, the temperature simulations were closer to the observations using the more accurate K_d values for the CTL and DARK simulations. Due to decreased water clarity, radiation absorbed in the top 1 m of the water body was larger for the DARK simulation and lower at greater depths than that observed for the CTL simulation. Such changes in radiation penetration in the DARK simulation generated a higher lake water surface temperature (LWST) and thus stronger lake-air interactions from February to July and lower LWST and turbulent fluxes from August to the following January than in the CTL simulation. The temperature inside the lake water body declined markedly, with a significant reduction from June to August that exceeded 5 °C. The results of this study provide an additional reference regarding lake water clarity effects on inland freshwater systems and theoretical support for lake water system management.

Monitoring and Predicting Channel Morphology of the Tongtian River, Headwater of the Yangtze River Using Landsat Images and Lightweight Neural Network

The Tongtian River is the source of the Yangtze River and is a national key ecological reserve in China. Monitoring and predicting the changes and mechanisms of the Tongtian River channel morphology are beneficial to protecting the “Asian Water Tower”. This study aims to quantitatively monitor and predict the accretion and erosion area of the Tongtian River channel morphology during the past 30 years (1990–2020). Firstly, the water bodies of the Tongtian River were extracted and the accretion and erosion areas were quantified using 1108 Landsat images based on the combined method of three water-body indices and a threshold, and the surface-water dataset provided by the European Commission Joint Research Centre. Secondly, an intelligent lightweight neural-network model was constructed to predict and analyze the accretion and erosion area of the Tongtian River. Results indicate that the Tongtian River experienced apparent accretion and erosion with a total area of 98.3 and 94.9 km2, respectively, during 1990–2020. The braided (meandering) reaches at the upper (lower) Tongtian River exhibit an overall trend of accretion (erosion). The Tongtian River channel morphology was determined by the synergistic effect of sediment-transport velocity and streamflow. The lightweight neural network well-reproduced the complex nonlinear processes in the river-channel morphology with a final prediction error of 0.0048 km2 for the training session and 4.6 km2 for the test session. Results in this study provide more effective, reasonable, and scientific decision-making aids for monitoring, protecting, understanding, and mining the evolution characteristics of rivers, especially the complex change processes of braided river channels in alpine regions and developing countries.