Search

The rapid and precise acquisition of the agricultural plastic greenhouse (PG) spatial distribution is essential in understanding PG usage and degradation, ensuring agricultural production, and protecting the ecological environment and human health. It is of great practical significance to realize the effective utilization of remote sensing images in the agricultural field and improve the extraction accuracy of PG remote sensing data. In this study, Landsat operational land imager (OLI) remote sensing images were used as data sources, and Shandong Province, which has the largest PG distribution in China, was selected as the study area. PGs in the study area were identified by means of contour recognition, feature set construction of the spatial structure, and machine learning. The results were as follows. (1) Through an optimal segmentation parameter approach, it was determined that the optimal segmentation scale for size, shape, and compactness should be set at 20, 0.8, and 0.5, respectively, which significantly improved PG contour recognition. (2) Among the 72 feature variables for PG spatial recognition, the number of features and classification accuracy showed a trend of first gradually increasing and then decreasing. Among them, fifteen feature variables, including the mean of bands 2 and 5; six index features (NDWI, GNDVI, SWIR1_NIR, NDVI, and PMLI); two shape features, the density and shape index; and two texture features, the contrast and standard deviation, played an important role. (3) According to the recall rate, accuracy rate, and F-value of three machine learning methods, random forest (RDF), CART decision tree (CART), and support vector machine (SVM), SVM had the best classification effect. The classification method described in this paper can accurately extract continuous plastic greenhouses through remote sensing images and provide a reference for the application of facility agriculture and non-point-source pollution control. [ABSTRACT FROM AUTHOR]

Soil salinization is a critical and global environmental problem. Effectively mapping and monitoring the spatial distribution of soil salinity is essential. The main aim of this work was to map soil salinity in Shandong Province located on the Yellow River Delta of China using Sentinel-1/2 remote sensing data and digital elevation model (DEM) data, coupled with soil sampling data, and combined with four regression models: support vector regression (SVR), stepwise multi-regression (SMR), partial least squares regression (PLSR) and random forest regression (RFR). For these purposes, 60 soil samples were collected during the field survey conducted from 9 to 14 October 2019, corresponding to the Sentinel-1/2 and DEM data. Then we established a soil salinity and feature dataset based on the sampled data and the features extracted from Sentinel-1/2 and DEM data. This study adopted the feature importance of the RF model to screen all features. The results showed that the CRSI index made the greatest contribution in retrieving soil salinity in this region. In this paper, 18 sampling points were used to validate and compare the performance of the four models. The results reveal that, compared with the other regression models, the PLSR model has the best performance (R2 = 0.66, and RMSE = 1.30). Finally, the PLSR method was used to predict the spatial distribution of soil salinity in the Yellow River Delta. We concluded that the model can be used effectively for the quantitative estimation of soil salinity and provides a useful tool for ecological construction. [ABSTRACT FROM AUTHOR]

Background: Accurate and reliable predictions of infectious disease can be valuable to public health organizations that plan interventions to decrease or prevent disease transmission. A great variety of models have been developed for this task. However, for different data series, the performance of these models varies. Hepatitis E, as an acute liver disease, has been a major public health problem. Which model is more appropriate for predicting the incidence of hepatitis E? In this paper, three different methods are used and the performance of the three methods is compared. Methods: Autoregressive integrated moving average(ARIMA), support vector machine(SVM) and long short-term memory(LSTM) recurrent neural network were adopted and compared. ARIMA was implemented by python with the help of statsmodels. SVM was accomplished by matlab with libSVM library. LSTM was designed by ourselves with Keras, a deep learning library. To tackle the problem of overfitting caused by limited training samples, we adopted dropout and regularization strategies in our LSTM model. Experimental data were obtained from the monthly incidence and cases number of hepatitis E from January 2005 to December 2017 in Shandong province, China. We selected data from July 2015 to December 2017 to validate the models, and the rest was taken as training set. Three metrics were applied to compare the performance of models, including root mean square error(RMSE), mean absolute percentage error(MAPE) and mean absolute error(MAE). Results: By analyzing data, we took ARIMA(1, 1, 1), ARIMA(3, 1, 2) as monthly incidence prediction model and cases number prediction model, respectively. Cross-validation and grid search were used to optimize parameters of SVM. Penalty coefficient C and kernel function parameter g were set 8, 0.125 for incidence prediction, and 22, 0.01 for cases number prediction. LSTM has 4 nodes. Dropout and L2 regularization parameters were set 0.15, 0.001, respectively. By the metrics of RMSE, we obtained 0.022, 0.0204, 0.01 for incidence prediction, using ARIMA, SVM and LSTM. And we obtained 22.25, 20.0368, 11.75 for cases number prediction, using three models. For MAPE metrics, the results were 23.5%, 21.7%, 15.08%, and 23.6%, 21.44%, 13.6%, for incidence prediction and cases number prediction, respectively. For MAE metrics, the results were 0.018, 0.0167, 0.011 and 18.003, 16.5815, 9.984, for incidence prediction and cases number prediction, respectively. Conclusions: Comparing ARIMA, SVM and LSTM, we found that nonlinear models(SVM, LSTM) outperform linear models(ARIMA). LSTM obtained the best performance in all three metrics of RSME, MAPE, MAE. Hence, LSTM is the most suitable for predicting hepatitis E monthly incidence and cases number. [ABSTRACT FROM AUTHOR]

Short-term load forecasting plays a significant role in the operation of power systems. Recently, deep learning has been generally employed in short-term load forecasting, primarily in the extraction of the characteristics of digital information in a single dimension without taking into account of the impact of external variables, particularly non-digital elements on load characteristics. In this paper, we propose a joint MFF-SAM-GCN to realize short-term load forecasting. First, we utilize a Bi-directional Long Short-Term Memory (Bi-LSTM) network and One-Dimensional Convolutional Neural Network (1D-CNN) in parallel connection to form a multi-feature fusion (MFF) framework, which can extract spatiotemporal correlation features of the load data. In addition, we introduce a Self-Attention Mechanism (SAM) to further enhance the feature extraction capability of the 1D-CNN network. Then with the deployment of a Graph Convolutional Network (GCN), the external non-digital features such as weather, strength, and direction of wind, etc., are extracted. Moreover, the generated weight matrices are incorporated into the load features to enhance feature recognition ability. Finally, we exploit Bayesian Optimization (BO) to find the optimal hyperparameters of the model to further improve the prediction accuracy. The simulation is taken from our proposed model and six benchmark schemes by using the bus load dataset of the Shandong Open Data Network, China. The results show that the RMSE of our proposed MFF-SAM-GCN model is 0.0284, while the SMAPE is 9.453%,the MBE is 0.025, and R-squared is 0.989, which is better than the selected three traditional machine learning methods and the three deep learning models. [ABSTRACT FROM AUTHOR]

This study represents the first application of Sentinel-2 remote sensing imagery and model fusion techniques to assess the chlorophyll-a (Chla) concentration and turbidity in Nansi Lake, Shandong Province, China, from 2016 to 2022. First, we innovatively employed the stacking method to fuse eight fundamentally different Machine Learning (ML) models, each utilising 20 and 17 feature bands, resulting in the development of a robust algorithm for estimating the Chla concentration and turbidity in Nansi Lake. The results demonstrate that the Stacking Model has achieved outstanding theoretical generalisation capability. Second, the sensitivity of the model to extreme value data in the sample was quantified, and we found that compared with extreme gradient boosting (XGBoost), the optimal performance of the Stacking Model improved by 12%, to some extent, it solved the problem of high-value underestimation and low-value overestimation. The SHapley Additive exPlanations (SHAP) results revealed that features such as Three Bands, Enhanced Three, R rs 492 / R rs 560 , R rs 705 / R rs 665 play a crucial role in estimating Chla concentration. For the turbidity estimation, the Normalized Difference Turbidity Index (NDTI), R rs 705 + R rs 560 , R rs 865 - R rs 740 made significant contributions. Finally, we utilised the Stacking Model to create spatiotemporal maps of the Chla concentration and turbidity in Nansi Lake from 2016 to 2022. We analysed the causes of the water quality changes and explored the driving factors. Compared with previous studies, this paper provides a new idea for the monitoring of lake water quality parameters by using the high resolution of Sentinel-2 image and the high precision of model fusion technology, these results can provide a reference for similar water area research and decision-making support for environment-related departments. • Innovatively fusion 8 algorithms with different principles, a robust algorithm suitable for estimating Chla and turbidity has been developed. • The SHAP was used to identify the key variables for Chla and turbidity of the lake. • Remote sensing mapping of Chla and turbidity in Nansi Lake, for the years 2016-2022 on quarterly and annual bases. • We analysed the spatiotemporal variations in the water quality of Nansi Lake, from 2016 to 2022. [ABSTRACT FROM AUTHOR]

Land use is a process that turns a piece of land's natural ecosystem into an artificial one. The mix of plant and man-made covers on the Earth's surface is known as land cover. Land use is the primary external force behind change in land cover, and land cover has an impact on how land use is carried out, resulting in a synergistic interaction between the two at the Earth's surface. In China's Shandong Peninsula city cluster, Dongying is a significant coastal port city. It serves as the administrative hub for the Yellow River Delta and is situated in Shandong Province, China's northeast. The changes in its urban land use and land cover in the future are crucial to understanding. This research suggests a prediction approach that combines a patch-generation land use simulation (PLUS) model and long-term short-term memory (LSTM) deep learning algorithm to increase the accuracy of predictions of future land use and land cover. The effectiveness of the new method is demonstrated by the fact that the average inaccuracy of simulating any sort of land use in 2020 is around 5.34%. From 2020 to 2030, 361.41 km2 of construction land is converted to cropland, and 424.11 km2 of cropland is converted to water. The conversion areas between water and unused land and cropland are 211.47 km2 and 148.42 km2, respectively. The area of construction land and cropland will decrease by 8.38% and 3.64%, respectively, while the area of unused land, water, and grassland will increase by 5.53%, 2.44%, and 0.78%, respectively. [ABSTRACT FROM AUTHOR]

• A machine-learning-based method is proposed to predict the coastal algal blooms with environmental factors. • We perform the experiments on the real data of China and United States, respectively to identify key features. • The phytoplankton concentration can be predicted one or two weeks in advance by the GBDT model. Harmful algal blooms are a major type of marine disaster that endangers the marine ecological environment and human health. Since the algal bloom is a complex nonlinear process with time characteristics, traditional statistical methods often cannot provide good predictions. In this paper, we propose a method based on machine learning with the aim to predict the occurrence of algal blooms by environmental parameters. The features related to algal bloom growth have been experimented for achieving a good prediction of algal concentrations by a combination strategy. We validate the prediction performance on two real datasets from two locations in US and China, i.e., Scripps Pier, California and Sishili Bay, Shandong, respectively. The models and feature subsets have been selected to complete the missing data and predict the phytoplankton concentration. The results demonstrate the efficiency of our method in the short-term prediction of concentrations by selecting appropriate features. The comparison studies prove the advantage of our developed machine learning method. The importance of every features for the prediction performance reveals crucial factors for the outbreak of harmful algal blooms. [ABSTRACT FROM AUTHOR]