Search

Wintertime precipitation, especially snowstorms, significantly impacts people's lives. However, the current forecast skill of wintertime precipitation is still low. Based on data augmentation (DA) and deep learning, we propose a DABU‐Net which improves the Global Forecast System wintertime precipitation forecast over southeastern China. We build three independent models for the forecast lead times of 24, 48, and 72 hr, respectively. After using DABU‐Net, the mean Root Mean Squared Errors (RMSEs) of the wintertime precipitation at the three lead times are reduced by 19.08%, 25.00%, and 22.37%, respectively. The threat scores (TS) are all significantly increased at the thresholds of 1, 5, 10, 15, and 20 mm day−1 for the three lead times. During heavy precipitation days, the RMSEs are decreased by 14% and TS are increased by 7% at the lead times within 48 hr. Therefore, combining DA and deep learning has great prospects in precipitation forecasting. Plain Language Summary: In this paper, we propose a deep learning‐based method to improve the forecast performance of Global Forecast System wintertime precipitation over southeastern China. Due to the imbalanced distribution of precipitation data, we use data from the three other seasons as an augmented data set for wintertime precipitation to train the deep neural network. The results show that the method can reduce the Root Mean Squared Error and improve the TS, a metric of precipitation forecast performance, of the precipitation. In particular, TS at the threshold of 20 mm day−1 are increased by 69.23%, 90.00%, and 100.00% at lead times of 24, 48, and 72 hr. The proposed method performs well during heavy precipitation days at lead times within 48 hr. Combining data augmentation with deep learning provides a successful approach to predicting precipitation. Key Points: A deep learning model based on data augmentation (DA) is proposed to improve the Global Forecast System wintertime precipitation forecastThe deep learning model improves the heavy precipitation forecast at lead times within 48 hrDA plays a critical role in the heavy precipitation forecast [ABSTRACT FROM AUTHOR]

Data assimilation techniques are one of the most important ways to reduce the uncertainty in atmospheric chemistry model input and improve the model forecast accuracy. In this paper, an ensemble optimal interpolation assimilation (EnOI) system for a regional online chemical weather numerical forecasting system (GRAPES_Meso5.1/CUACE) is developed for operational use and efficient updating of the initial fields of chemical components. A heavy haze episode in eastern China was selected, and the key factors affecting EnOI, such as localization length scale, ensemble size, and assimilation moment, were calibrated by sensitivity experiments. The impacts of assimilating ground-based PM 2.5 observations on the model chemical initial field PM 2.5 and visibility forecasts were investigated. The results show that assimilation of PM 2.5 reduces the uncertainty in the initial PM 2.5 field considerably. Using only 50 % of observations in the assimilation, the root mean square error (RMSE) of initial PM 2.5 for independent verification sites in mainland China decreases from 73.7 to 46.4 µ g m -3 , and the correlation coefficient increases from 0.58 to 0.84. An even larger improvement appears in northern China. For the forecast fields, assimilation of PM 2.5 improves PM 2.5 and visibility forecasts throughout the time window of 24 h. The PM 2.5 RMSE can be reduced by 10 %–21 % within 24 h, and the assimilation effect is the most remarkable in the first 12 h. Within the same assimilation time, the assimilation efficiency varies with the discrepancy between model forecasts and observations at the moment of assimilation, and the larger the deviation, the higher the efficiency. The assimilation of PM 2.5 further contributes to the improvement of the visibility forecast. When the PM 2.5 increment is negative, it corresponds to an increase in visibility, and when the PM 2.5 analysis increment is positive, visibility decreases. It is worth noting that the improvement of visibility forecasting by assimilating PM 2.5 is more obvious in the light-pollution period than in the heavy-pollution period. The results of this study show that EnOI may provide a practical and cost-effective alternative to the ensemble Kalman filter (EnKF) for the applications where computational cost is the main limiting factor, especially for real-time operational forecast. [ABSTRACT FROM AUTHOR]

In this paper, a Comprehensive Diagram Method (CDM) for a Multi-Layer Perceptron Neuron Network (MLPNN) is proposed to realize natural gas energy metering using temperature, pressure, and the speed of sound from an ultrasonic flowmeter. Training and testing of the MLPNN model were performed on the basis of 1003 real data points describing the compression factors (Z-factors) and calorific values of the three main components of natural gas in Sichuan province, China. Moreover, 20 days of real tests were conducted to verify the measurements' accuracy and the adaptability of the new intelligent method. Based on the values of the Mean Relative Errors and the Root Mean Square errors for the learning and test errors calculated on the basis of the actual data, the best-quality MLP 3-5-1 network for the metering of Z-factors and the new CDM methods for the metering of calorific values were experimentally selected. The Bayesian regularized MLPNN (BR-MLPNN) 3-5-1 network showed that the Z-factors of natural gas have a maximum relative error of −0.44%, and the new CDM method revealed calorific values with a maximum relative error of 1.90%. In addition, three local tests revealed that the maximum relative error of the daily cumulative amount of natural gas energy was 2.39%. [ABSTRACT FROM AUTHOR]

On 25 July 2021, the AUV of the Marine Science and Technology Research Center was lost under the sea due to a fracture of the wire rope when it was performing a mission offshore of China. A model is presented in the paper for predicting the trajectory of a lost AUV based on ABiLSTM. To increase the precision of model prediction, the model incorporates the soft attention mechanism and is based on the bidirectional Long Short-Term Memory (BiLSTM) network. In comparison to LSTM, BiLSTM, and attention-LSTM models, experiments have demonstrated that the proposed model enhanced prediction accuracy in terms of longitude, latitude, and altitude by 0.009° E, 0.008° N, and 2 m using representative root mean squared error as an assessment indicator. The findings of the study can improve marine rescue efforts and aid in the search and recovery of AUVs that have crashed. [ABSTRACT FROM AUTHOR]

In this paper, we forecasted the ionospheric total electron content (TEC) over the region of China using the bidirectional convolutional gated recurrent unit (BiConvGRU) model. We first generated the China Regional Ionospheric Maps (CRIMs) using GNSS observations provide by the Crustal Movement Observation Network of China (CMONOC). We then used gridded TEC maps from 2015 to 2018 with a 1 h interval from the CRIMs as the dataset, including quiet periods and storm periods of ionospheric TEC. The BiConvGRU model was then utilized to forecast the ionospheric TEC across China for the year 2018. The forecasted TEC was compared with the TEC from the International Reference Ionosphere (IRI-2016), Convolutional Long Short-Term Memory (ConvLSTM), Convolutional Gated Recurrent Unit (ConvGRU), Bidirectional Convolutional Long Short-Term Memory (BiConvLSTM), and the 1-day Predicted Global Ionospheric Map (C1PG) provided by the Center for Orbit Determination in Europe (CODE). In addition, indices including Kp, ap, Dst and F10.7 were added to the training dataset to improve the forecasting accuracy of the model (-A indicates no indices, while -B indicates with indices). The results verified that the prediction accuracies of the models integrated with these indices were significantly improved, especially during geomagnetic storms. The BiConvGRU-B model presented a decrease of 41.5%, 22.3%, and 13.2% in the root mean square error (RMSE) compared to the IRI-2016, ConvGRU, and BiConvLSTM-B models during geomagnetic storm days. Furthermore, at a specific grid point, the BiConvGRU-B model showed a decrease of 42.6%, 49.1%, and 31.9% in RMSE during geomagnetic quiet days and 30.6%, 34.1%, and 15.1% during geomagnetic storm days compared to the IRI-2016, C1PG, and BiConvLSTM-B models, respectively. In the cumulative percentage analysis, the BiConvGRU-B model had a significantly higher percentage of mean absolute error (MAE) within the range of 0–1 TECU in all seasons compared to the BiConvLSTM-B model. Meanwhile, the BiConvGRU-B model outperformed the BiConvLSTM-B model with lower RMSE for each month of 2018. [ABSTRACT FROM AUTHOR]

Landslides are a major concern in the mountainous regions of southwest China, leading to significant loss of life and property damage. Therefore, it is crucial to identify potential landslides for early warning and mitigation. stacking-InSAR, a technique used for landslide identification in a wide area, has been found to be faster than conventional time-series InSAR. However, the dense vegetation in southwest China mountains has an adverse impact on the coherence of stacking-InSAR, resulting in more noise and inaccuracies in landslide identification. To address this problem, this paper proposes an improved seasonal interferometry stacking-InSAR method. It uses Sentinel-1 satellite data from 2017 to 2022. The study area is the river valley section of the G213 road from Wenchuan County to Mao County. The study reveals the characteristics of seasonal decoherence in the steep mountainous region, and identifies a total of 21 potential landslides using the improved method. Additionally, optical satellite imagery and LiDAR data were used to assist in the identification of potential landslides. The results of the conventional stacking-InSAR method and the improved seasonal interferometry stacking-InSAR method are compared, showing that the latter is more effective in noise suppression caused by low coherence. Their standard deviations were reduced by 46%, 22%, 10%, and 14%, respectively, using the quantitative statistics for the four tested areas. The proposed method provides an efficient and effective approach for detecting potential landslides in the mountainous regions of southwest China. It can serve as a valuable technical reference for future landslide identification studies in this area. [ABSTRACT FROM AUTHOR]

To improve the accuracy and reliability of precipitation estimation, numerous models based on machine learning technology have been developed for integrating data from multiple sources. However, little attention has been paid to extracting the spatiotemporal correlation patterns between satellite products and rain gauge observations during the merging process. This paper focuses on this issue by proposing an integrated framework to generate an accurate and reliable spatiotemporal estimation of precipitation. The proposed framework integrates Funk-Singular Value Decomposition (F-SVD) in the recommender system to achieve the accurate spatial distribution of precipitation based on the spatiotemporal interpolation of rain gauge observations and Convolutional Long Short-Term Memory (ConvLSTM) to merge precipitation data from interpolation results and satellite observation through exploiting the spatiotemporal correlation pattern between them. The framework (FS-ConvLSTM) is utilized to obtain hourly precipitation merging data with a resolution of 0.1° in Jianxi Basin, southeast of China, from both rain gauge data and Global Precipitation Measurement (GPM) from 2006 to 2018. The LSTM and Inverse Distance Weighting (IDW) are constructed for comparison purposes. The results demonstrate that the framework could not only provide more accurate precipitation distribution but also achieve better stability and reliability. Compared with other models, it performs better in variation process description and rainfall capture capability, and the root mean square error (RSME) and probability of detection (POD) are improved by 63.6% and 22.9% from the original GPM, respectively. In addition, the merged precipitation combines the strength of different data while mitigating their weaknesses and has good agreement with observed precipitation in terms of magnitude and spatial distribution. Consequently, the proposed framework provides a valuable tool to improve the accuracy of precipitation estimation, which can have important implications for water resource management and natural disaster preparedness. [ABSTRACT FROM AUTHOR]

The objective of this paper is to perform drip irrigation scheduling for spinach (Spinacia oleracea L.) in a plastic greenhouse using the standard 20 cm evaporation pan. A drip irrigation experiment with four levels of irrigation, i.e., 0.6, 0.8, 1.0, and 1.2 times the cumulative evaporation of a 20 cm standard pan (Epan) were set up. The irrigation interval was controlled using a 20 mm Epan, and optimal irrigation water amounts of 0.8 Epan and 0.6 Epan were recommended for the spring and autumn growing seasons, respectively. Overirrigation (1.2 Epan) also led to yield losses, particularly for stem growth. In addition, a proper greenhouse index, defined as the ratio of the cumulative Epan inside and outside the greenhouse, could predict the Epan inside the greenhouse using the external Epan to a high degree of accuracy (daily data with r2 = 0.85, root mean square error (RMSE = 0.68 mm d−1), for a 4-day interval with r2 = 0.95, RMSE = 1.81 mm 4 day−1, and for the entire growth period with r2 = 1.0, RMSE = 2.40 mm). A simple and low-cost greenhouse index method could be used to formulate drip irrigation schedules for spinach in low-technology plastic greenhouses using a 20 cm standard pan outside the greenhouse. [ABSTRACT FROM AUTHOR]

To assess and predict the food safety risk of benzopyrene (BaP) in edible oils in China, this study collected national sampling data of edible oils from 20 Chinese provinces and their prefectures in 2019, and constructed a risk assessment model of BaP in edible oils with consumption data. Initially, the k-means algorithm was used for risk classification; then the data were pre-processed and trained to predict the data using the Long Short-Term Memory (LSTM) and the eXtreme Gradient Boosting (XGBoost) models, respectively, and finally, the two models were combined using the inverse error method. To test the effectiveness of the prediction model, this study experimentally validated the model according to five evaluation metrics: root mean square error (RMSE), mean absolute error (MAE), precision, recall, and F1 score. The variable-weight combined LSTM-XGBoost prediction model proposed in this paper achieved a precision of 94.62%, and the F1 score value reached 95.16%, which is significantly better than other neural network models; the results demonstrate that the prediction model has certain stability and feasibility. Overall, the combined model used in this study not only improves the accuracy but also enhances the practicality, real-time capabilities, and expandability of the model. [ABSTRACT FROM AUTHOR]

The Decision Support System for Agrotechnology transfer (DSSAT) is a global modelling platform that encompasses crop models for more than 40 different crops. The models have been used extensively throughout the world, including South Asia and China. From the web of science database, we reviewed 205 papers that were published from January 2010 to February 2022 containing examples of the evaluation and application of the DSSAT crop simulation models. In South Asia and China, more than 50 traits and variables were analyzed for various experiments and environmental conditions during this period. The performance of the models was evaluated by comparing the simulated data with the observed data through different statistical parameters. Over the years and across different locations, the DSSAT crop models simulated phenology, growth, yield, and input efficiencies reasonably well with a high coefficient of determination (R²), and Willmott d-index, together with a low root mean square error (RMSE), normalized RMSE (RMSEn), mean error (ME) or percentage error difference. The CERES models for rice, wheat and maize were the most used models, followed by the CROPGRO models for cotton and soybean. Grain yield, anthesis and maturity dates, above ground biomass, and leaf area index were the variables that were evaluated most frequently for the different crop models. The meta-analysis of the data of the most common simulated variables (Anthesis, maturity, leaf area index, grain yield and above ground biomass) for the four commonly used DSSAT models (CERES-Rice, CERES-Wheat, CERES-Maize and CROPGRO-Cotton) showed that the models predicted anthesis with an RMSE of ~2 (CERES-Maize) and -4 days (CERES-Wheat), a normalized RMSE of ~2.5 (CERES-Maize) and -3.8% (CERES-Rice), and a R² ~ 0.98-0.99. The maturity was predicted with an RMSE~ 3.0 (CERES-Maize)-6.1 days (CROPGRO-Cotton), normalized RMSE~2.3 (CERES-Wheat)-5.0% (CERES-Rice) and R² ~ 0.90-0.99. The leaf area index was predicted with an RMSE~ 0.3-0.7, normalized RMSE~6 (CROPGRO-Cotton)-16% (CERES-Maize) and R² ~ 0.75-0.98. The model performance for simulating grain yield was best with CROPGRO-cotton with a normalized RMSE of 4.4%, RMSE of 138.8 kg and R² of 0.99. The lowest R² and highest RMSEn was found for CERES-Wheat. Among all the variables that were evaluated, above ground biomass was least accurately simulated with a RMSEn as high as 18% and R² as small as 0.50 by CERES-Wheat. The models were used for studying the crop response under various soil, weather, and management conditions. The review will be helpful to identify the research gap in the use of crop models for different crops in South Asia and China. It can also aid scientists to target their research for specific applications to address food and nutrition security based on sustainable management practices. [ABSTRACT FROM AUTHOR]

Block Adjustment (BA) is one of the essential techniques for producing high-precision geospatial 3D data products with optical stereo satellite imagery. For block adjustment with few ground-control points or without ground control, the vertical error of the model is the decisive factor that constrains the accuracy of 3D data products. The elevation data obtained by spaceborne laser altimeter have the advantages of short update periods, high positioning precision, and low acquisition cost, providing sufficient data support for improving the elevation accuracy of stereo models through the combined BA. This paper proposes a geometric positioning model based on the integration of Optical Satellite Stereo Imagery (OSSI) and spaceborne laser altimeter data. Firstly, we elaborate the principle and necessity of this work through a literature review of existing methods. Then, the framework of our geo-positioning models. Secondly, four key technologies of the proposed model are expounded in order, including the acquisition and management of global Laser Control Points, the association of LCPs and OSSI, the block adjustment model combining LCPs with OSSI, and the accuracy estimation and quality control of the combined BA. Next, the combined BA experiment using Ziyuan-3 (ZY-3) OSSI and ICESat-2 laser data was carried out at the testing site in Shandong Province, China. Experimental results prove that our method can automatically select LCPs with high accuracy. The elevation deviation of the combined BA eventually achieved the Mean Error (ME) of 0.06 m and the Root Mean Square Error (RMSE) of 1.18 m, much lower than the ME of 13.20 m and the RMSE of 3.88 m before the block adjustment. A further research direction will be how to perform more adequate accuracy analysis and quality control using massive laser points as checkpoints. [ABSTRACT FROM AUTHOR]

Landslide deformation is affected by its geological conditions and many environmental factors. So it has the characteristics of dynamic, nonlinear and unstable, which makes the prediction of landslide displacement difficult. In view of the above problems, this paper proposes a dynamic prediction model of landslide displacement based on the improvement of complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), approximate entropy (ApEn) and convolution long short-term memory (CNN-LSTM) neural network. Firstly, ICEEMDAN and ApEn are used to decompose the cumulative displacements into trend, periodic and random displacements. Then, the least square quintic polynomial function is used to fit the displacement of trend term, and the CNN-LSTM is used to predict the displacement of periodic term and random term. Finally, the displacement prediction results of trend term, periodic term and random term are superimposed to obtain the cumulative displacement prediction value. The proposed model has been verified in Bazimen landslide in the Three Gorges Reservoir area of China. The experimental results show that the model proposed in this paper can more effectively predict the displacement changes of landslides. As compared with long short-term memory (LSTM) neural network, gated recurrent unit (GRU) network model and back propagation (BP) neural network, CNN-LSTM neural network had higher prediction accuracy in predicting the periodic displacement, with the mean absolute percentage error (MAPE) reduced by 3.621%, 6.893% and 15.886% respectively, and the root mean square error (RMSE) reduced by 3.834 mm, 3.945 mm and 7.422 mm respectively. Conclusively, this model not only has high prediction accuracy but also is more stable, which can provide a new insight for practical landslide prevention and control engineering. [ABSTRACT FROM AUTHOR]

The issue of renewable energy curtailment poses a crucial challenge to its effective utilization. To address this challenge, mitigating the impact of the intermittency and volatility of wind and solar energy is essential. In this context, this paper employs scenario analysis to examine the complementary features of wind and solar hybrid systems. Firstly, the study defines two types of complementary indicators that distinguish between output smoothing and source-load matching. Secondly, a novel method for generating wind and solar output scenarios based on improved Generative Adversarial Networks is presented and compared against the conventional Monte Carlo and Copula function methods. Lastly, the generated wind and solar scenarios are employed to furnish complementary features. The testing results across eight regions indicate the proposed scenario generation method proficiently depicts the historical relevance as well as future uncertainties. This study found that compared to the Copula function method, the root mean square error of the generated data was reduced by 4% and 3.4% for independent and hybrid systems, respectively. Moreover, combining these two resources in most regions showed that the total output smoothness and source-load matching level cannot be enhanced simultaneously. This research will serve as a valuable point of reference for planning and optimizing hybrid systems in China. [ABSTRACT FROM AUTHOR]

Background: Infectious diseases are a major threat to public health, causing serious medical consumption and casualties. Accurate prediction of infectious diseases incidence is of great significance for public health organizations to prevent the spread of diseases. However, only using historical incidence data for prediction can not get good results. This study analyzes the influence of meteorological factors on the incidence of hepatitis E, which are used to improve the accuracy of incidence prediction. Methods: We extracted the monthly meteorological data, incidence and cases number of hepatitis E from January 2005 to December 2017 in Shandong province, China. We employ GRA method to analyze the correlation between the incidence and meteorological factors. With these meteorological factors, we achieve a variety of methods for incidence of hepatitis E by LSTM and attention-based LSTM. 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: Duration of sunshine and rainfall-related factors(total rainfall, maximum daily rainfall) are more relevant to the incidence of hepatitis E than other factors. Without meteorological factors, we obtained 20.74%, 19.50% for incidence in term of MAPE, by LSTM and A-LSTM, respectively. With meteorological factors, we obtained 14.74%, 12.91%, 13.21%, 16.83% for incidence, in term of MAPE, by LSTM-All, MA-LSTM-All, TA-LSTM-All, BiA-LSTM-All, respectively. The prediction accuracy increased by 7.83%. Without meteorological factors, we achieved 20.41%, 19.39% for cases in term of MAPE, by LSTM and A-LSTM, respectively. With meteorological factors, we achieved 14.20%, 12.49%, 12.72%, 15.73% for cases, in term of MAPE, by LSTM-All, MA-LSTM-All, TA-LSTM-All, BiA-LSTM-All, respectively. The prediction accuracy increased by 7.92%. More detailed results are shown in results section of this paper. Conclusions: The experiments show that attention-based LSTM is superior to other comparative models. Multivariate attention and temporal attention can greatly improve the prediction performance of the models. Among them, when all meteorological factors are used, multivariate attention performance is better. This study can provide reference for the prediction of other infectious diseases. [ABSTRACT FROM AUTHOR]

Nitrogen dioxide (NO2) is an important precursor of atmospheric aerosol. Forecasting urban NO2 concentration is vital for effective control of air pollution. This paper proposes a hybrid deep learning model for predicting daily average NO2 concentrations on the next day, based on atmospheric pollutants, meteorological data, and historical data during 2014 to 2020 in five coastal cities of Shandong peninsula, northern China. A random Forest (RF) algorithm was used to select input variables to reduce data dimensionality trained by the sequence to sequence (Seq2Seq) the model and describe how the Seq2Seq model understands each predictor variable. The hybrid model combining an RF with Seq2Seq network (RF-S2S) was evaluated and achieved a Pearson's correlation coefficient of 0.93, a Nash–Sutcliffe coefficient (NS) of 0.79, a Root Mean Square Error (RMSE) of 5.85 µg/m3, a Mean Absolute Error (MAE) of 4.50 µg/m3, and a Mean Absolute Percentage Error (MAPE) of 20.86%. Feature selection by an RF model improves the performance of the Seq2Seq model, reducing errors by 19.7% (RMSE), 20.3% (MAE), and 29.3% (MAPE), respectively. Carbon monoxide (CO) and PM10 are two common, important features influencing the prediction of NO2 concentrations in coastal areas of northern China. The results of RF-S2S models can capture general trends and disruptions more accurately than can long-short term memory (LSTM) models with and without feature selection. The decreasing tendency of NO2 from 2014 to 2020 illustrated by the empirical mode decomposition (EMD) method is one important obstacle to improving the RF-S2S prediction accuracy. An EMD-based RF-S2S model could help to perform the short-term forecast of NO2 concentrations efficiently. [ABSTRACT FROM AUTHOR]

Scientific prediction of the penetration rate (PR) of tunnel boring machines (TBMs) is of great significance to the selection of tunnel construction methods, the prediction of construction progress, and the evaluation of benefits. In view of the high nonlinearity, fuzziness, and complexity of the TBM excavation process, this paper attempts to present a new algorithm that integrates partial least squares regression (PLSR) with boosted regression trees (BRT) for predicting the PR of TBMs. For this purpose, 150 datasets were obtained from the Lanzhou water conveyance tunnel project in China. Six impact factors were selected as the input layers of the proposed model by single-factor correlation analysis. To develop the PLSR-BRT model, two principal components of the influencing parameters were extracted via the PLSR method, and the BRT algorithm was employed to establish the predictive model. In addition, other models such as PLSR back propagation neural network (BPNN), BRT, PLSR, support vector regression (SVR), and artificial neural network (ANN) were adapted for use in this problem to verify the predictive accuracy of the proposed model. The results demonstrated that the PLSR-BRT model achieved the best predictive performance compared with the other models, with coefficient of determination value (R2) and root mean square error (RMSE) of 0.96 and 1.78, respectively, for the testing set. The PLSR-BRT model can maximally avoid both overfitting and inadequate fitting. In view of engineering applications, the complexity and redundancy of the field dataset can be solved via reducing the dimensionality of input parameters, and the training samples could be expanded by a boosted method so that the discontinuously acquired geological parameters are unable to restrain the model performance. This method serves as an effective approach for TBM PR prediction and has excellent potential for a variety of scientific and engineering applications. [ABSTRACT FROM AUTHOR]

Precise Point Positioning (PPP) is an official service of the BeiDou Global Navigation Satellite System (BDS-3) through the PPP-B2b signal. In this paper, we mainly focus on the long-term performance evaluation of BDS-3 PPP-B2b products and their application in time service. Since the PPP-B2b product is only available in and around China area, the arcs of PPP-B2b products are about several hours. We propose to evaluate the time datum stability by using all available satellites. Then, 557 day PPP-B2b products are collected for this experiment. The results show that there are large jumps in the GPS satellite clock time datum series. However, the BDS-3 satellite clock datum stability is almost at the same level with current Space State Representation (SSR) corrections from the International Global navigation satellite system Service (IGS). The difference between PPP-B2b GPS and BDS-3 satellite clock time datum will be absorbed into the Inter System Bias (ISB) parameter. Thus, it should be specially noted that the ISB parameter cannot be estimated as constant values if users use PPP-B2b products. In addition, the accuracy of the BDS-3 satellite clock is significantly better than that of the GPS for both the Root Mean Square Error (RMSE) and standard deviation (STD). The average Signal in Space Range Errors (SISREs) is 0.22 ns and 0.13 ns for GPS and BDS-3, respectively. The one-way timing experiment shows BDS-3 timing stability is 2.9 × 10−14@104 s. In addition, 10 baselines from 13 km to 4494 km are formed for time synchronization evaluation by using PPP-B2b products. The average RMSEs of time synchronization is from 0.46 ns to 1.58 ns and from 0.66 ns to 1.19 ns for GPS and BDS-3, respectively. As for STD, the average values are from 0.27 ns to 0.74 ns and from 0.27 ns to 0.47 ns for GPS and BDS-3, respectively. Overall, the results show that the time datum stability, accuracy, and service performance of BDS-3 PPP-B2b products has been stable over the past two years. [ABSTRACT FROM AUTHOR]

Total phosphorus (TP) concentration is high in countless small inland waterbodies in Hubei province, middle China, which is threating the water environment. However, there are almost no ground-based water quality monitoring points in small inland waterbodies, because the cost of time, labor, and money is high and it does not meet the needs of spatiotemporal dynamic monitoring. Remote sensing provides an effective tool for TP concentration monitoring spatiotemporally. However, monitoring the TP concentration of small inland waterbodies is challenging for satellite remote sensing due to the inadequate spatial resolution. Recently, unmanned aerial vehicles (UAV) have been applied to quantitatively retrieve the spatiotemporal distribution of TP concentration without the challenges of cloud cover and atmospheric effects. Although state-of-the-art algorithms to retrieve TP concentration have been improved, specific models are only used for specific water quality parameters or regions, and there are no robust and reliable TP retrieval models for small inland waterbodies at this time. To address this issue, six machine learning methods optimized by intelligent optimization algorithms (IOA-ML models) have been developed to quantitatively retrieve TP concentration combined with the reflectance of original bands and selected band combinations of UAV multispectral images. We evaluated the performances of models in terms of coefficient of determination (R2), root mean squared error (RMSE), and residual prediction deviation (RPD). The results showed that the R2 of the six IOA-ML models for training, validation, and test sets were 0.8856–0.984, 0.8054–0.8929, and 0.7462–0.9045, respectively, indicating the methods had high precision and transferability. The extreme gradient boosting optimized by genetic algorithm (GA-XGB) performed best, with the highest precision for the validation and test sets. The spatial distribution of TP concentration of each flight derived from different models had similar distribution characteristics. This paper provides a reference for promoting the intelligent and automatic level of water environment monitoring in small inland waterbodies. [ABSTRACT FROM AUTHOR]

The scientific and accurate prediction of suspended sediment concentrations is of great importance for river management in the lower reaches of the Yellow River and for the scheduling of water conservancy projects in the upper and middle reaches. In order to solve the influence of the non-linear and non-smooth characteristics of the suspended sediment concentration series in the lower Yellow River on the prediction results and improve the prediction accuracy, this paper proposes a coupled model based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) and non-linear autoregressive (NAR) model. Take the predicted suspended sediment concentrations in the lower reaches of the Yellow River at the Huayuankou hydrographic station as an example. The accuracy and stability of the coupled CEEMD-NAR model were verified through the Gaocun and Lijin hydrological stations. The CEEMD-NAR model predicted suspended sediment concentrations with a Nash–Sutcliffe efficiency (NSE) factor of 0.93. The three statistical evaluation indicators of the CEEMD-NAR model, mean absolute error (MAE), mean relative error (MRE), and root mean square error (RMSE) were 2.12 kg/m3, 1.07, and 3.75 kg/m3 respectively. In contrast to the NAR, EMD-NAR, and EEMD-NAR models, the coupled CEEMD-NAR model has good stability and high prediction accuracy and can be used in non-linear, non-smooth suspended sediment concentration long series prediction. [ABSTRACT FROM AUTHOR]

Methane (CH4) is the second-largest greenhouse gas emitted by human activity and natural sources after carbon dioxide (CO2). Its relatively short lifetime in the atmosphere (about 12 years) means that we can mitigate the human impacts of climate change in a relatively short period of time by reducing CH4 emissions. The creation of CH4 emissions management policies can be based on the distribution maps of surface CH4 concentration that are in large-scale and at high-resolution. The estimate of CH4 emissions with broad coverage are provided by currently extensively used satellite data supplemented with data from model simulations. However, it is at low spatial resolution. In this paper, through the combination of atmospheric CH4 observations from the TROPOMI sensor and wind data from the ECMWF global reanalysis, a straightforward divergence method is proposed to estimate the surface CH4 emissions in China from March 2019 to September 2022 at a resolution of 7 km × 7 km. This method was compared with the average annual CH4 emissions of Emissions Database for Global Atmospheric Research (EDGARv7.0), and the Root Mean Square Error (RMSE) is 2.53 kg/km2/h and within error envelop (EE) is 72.93%, which represents the proportion of reliable values under certain uncertain conditions. We estimated that the average annual CH4 emissions in China from 2019 to 2022 is 81 Tg, with the lowest emissions in 2021 (75 Tg) due to the impact of COVID-19. In 2021, the largest anthropogenic emissions in China are from agriculture, energy activities and livestock, accounting for 28% (20.8 Tg), 25% (18.9 Tg) and 19% (13.9 Tg) of total emissions, respectively, while wetlands, as the largest natural source, produce 14% (10.5 Tg) of CH4 emissions. [ABSTRACT FROM AUTHOR]

Grain yield data based on administrative divisions (counties, cities, etc.) for statistics lack spatial information, which can be effectively solved by grain yield spatialization. This paper proposes a spatialization method for grain yield based on the Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) time series data. The method was tested by taking winter wheat (Triticum aestivum L.) in Shandong Province in China as an example. First, the classification and regression tree (CART) algorithm was trained to extract the winter wheat planting pixels in 2016. The average NDVIs of the different growing stages (returning green, jointing, heading, and milk ripening) were calculated from the MODIS NDVI time series data. The relationship between winter wheat yield and NDVI variables (including single-phase NDVI and the average NDVI of different growing stages) was analyzed by univariate and multiple linear regressions. The NDVI variable with the highest correlation to winter wheat yield and the minimum root mean square error of the fitting equation were chosen as input to build the spatialization model. The results show that the classification accuracy of winter wheat estimated with the confusion matrix was 82.51% and that the average precision of planting acreage compared with county-level statistical data was 87.64%. The average relative error of yield spatialization at the county level was 22.71%. The method developed in this paper is easy to operate and popularize, and it can provide a technical reference for producing high-resolution crop yield distribution maps of long time series through spatialization. [ABSTRACT FROM AUTHOR]

This paper combines discrete wavelet transform (DWT), autoregressive moving average (ARMA), and XGBoost algorithm to propose a weighted hybrid algorithm named DWTs-ARMA-XGBoost (DAX) on long-time temperature series analysis. Firstly, this paper chooses the temperature data of February 1 to 20 from 1967 to 2016 of northern mountainous area in North China as the observed data. Then, we use 10 different discrete wavelet functions to decompose and reconstruct the observed data. Next, we build ARMA models on all the reconstructed data. In the end, we regard the calculations of 10 DWT-ARMA (DA) algorithms and the observed data as the labels and target of the XGBoost algorithm, respectively. Through the data training and testing of the XGBoost algorithm, the optimal weights and the corresponding output of the hybrid DAX model can be calculated. Root mean squared error (RMSE) was followed as the criteria for judging the precision. This paper compared DAX with an equal-weighted average (EWA) algorithm and 10 DA algorithms. The result shows that the RMSE of the two hybrid algorithms is much lower than that of the DA algorithms. Moreover, the bigger decrease in RMSE of the DAX model than the EWA model represents that the proposed DAX model has significant superiority in combining models which proves that DAX has significant improvement in prediction as well. [ABSTRACT FROM AUTHOR]

The prediction and analysis of surrounding rock deformation is a primary risk assessment method in tunnel engineering. However, the accurate prediction result is not easy to achieve due to the influence of multiple factors such as rock mass properties, support structure, and the spatial effect of tunnel construction. In this paper, a multivariate time-series model (MTSM) for tunnel displacement prediction is studied based on Gaussian process regression (GPR) optimized by differential evolutionary (DE) strategy, where the spatial effect is intuitively expressed through an extended time-series model. First, building learning samples for GPR, in which the inputs is the displacement data of the previous n days and the output is the data of the day (n + 1). Then, for each sample, an input item is added successively to form an expanded learning sample, which is the "distance between the construction face and monitoring section" on the day (n + 1). Taking the root mean square error between the regression and measured data as the control index, the GPR model is trained to express the nonlinear mapping relationship between input and output, and the optimal parameters of this model are searched by DE. The displacement multivariate time-series model represented by DE-GPR is known as MTSM. On this basis, the applicability of GPR for tunnel displacement prediction and the necessity of DE optimization are illustrated by comparing the prediction results of several commonly used machine learning models. At the same time, the influence of GPR and DE parameters on the regression result and the computational efficiency of the MTSM model is analyzed, the recommendation for parameter values are given considering both calculation efficiency and accuracy. This method is successfully applied to the Leshanting tunnel of Puyan expressway in Fujian province, China, and the results show that the MTSM based on DE-GPR has a good ability in the deformation prediction of the surrounding rock, which provides a new method for tunnel engineering safety control. [ABSTRACT FROM AUTHOR]

It is of great significance to accurately grasp ground-level ozone concentration on a wide scale in order to cope with the increasingly serious ground-level ozone pollution problem. Currently, satellite technology can be used to monitor ground-level ozone concentration on a wide scale, but there is the problem of insufficient spatial resolution. The use of ground monitoring stations to detect ground-level ozone concentration can obtain more accurate ozone concentration around the station, but there are problems of limited number of stations and sparse distribution. Therefore, it is still a challenge to accurately grasp the ground-level ozone concentration at a large scale and high spatial resolution. To address this issue, this paper proposes a ground-level ozone concentration inversion algorithm based on deep learning methods, incorporating data from remote sensing satellites, ground monitoring stations, meteorological conditions, geography, and land use. Taking Yunnan Province in China as the experimental region and utilizing five-fold cross-validation, the model's Mean Square Error (MSE) reached 340.45 and Root Mean Square Error (RMSE) reached 18.45. Compared to machine learning models, the error decreased by 14.53%, outperforming Random Forest models, Convolution Neural Networks, and Vision Transformers. This study offers a referential approach for accurately capturing ground-level ozone concentrations at a large scale with high spatial resolution. [ABSTRACT FROM AUTHOR]

This paper provides the first experimental evidence of how admission outcomes in centralized systems depend on strategic college choice behaviors. Centralized college admissions simplify the application process and reduce students' informational barriers. However, such systems also reward informed and strategic college choices. In particular, centralized admissions can be difficult to navigate because they require students to understand how application portfolios and placement priorities map to admission probabilities. Using administrative data from one of the poorest provinces in China, I document that students made undermatched college choices that correlated with inaccurate predictions of admission probabilities. I then implemented a large-scale randomized experiment (N = 32,834) to provide treated students with either (a) an application guidebook or (b) a guidebook plus a school workshop. Results suggest that informing students on choosing colleges and majors based on precise predictions of admission probabilities can effectively improve student–college academic match by 0.1 to 0.2 standard deviation among compliers without substantially changing their college-major preferences. [ABSTRACT FROM AUTHOR]

We examine the impact of early-life famine experiences on commercial insurance demand in this paper. Using household-level data from China, we show that household heads' famine experiences in early adulthood have a causal relationship with the household's commercial insurance demand. When the famine severity increases by one standard deviation, the probability of the household purchasing insurance rises by 2.97%, and the premium expense increases by 23.04%. The results remain robust when we account for alternative definitions of cohorts and famine severity measurements and migration after the Great Famine. Finally, we show that the mechanism behind the causative effects is due to the Great Famine-related change in risk preference. After the famine, people became more risk averse and more likely to buy commercial insurance in their later life. [ABSTRACT FROM AUTHOR]

This paper examines upstream propagations of the US–China tariff war in 2018–2019 through the lens of exports from 32 countries to China. Building an industry-country specific measure of input–output linkages with China, we obtain new empirical evidence that the US tariffs on Chinese imports had a significant adverse effect on third countries by dampening Chinese demand for foreign inputs. A one standard deviation rise in this upstream shock leads to a decline in the growth rate of exports to China by 2.6 percentage points. A quantification exercise shows that the upstream propagation of US tariffs has incurred an average GDP loss of 0.05 percent for these countries. Taiwan and Korea, key suppliers to China, were most severely hurt by this vertical effect. Firm-level analysis using a panel of Korean manufacturers lends further support to the importance of this vertical linkage channel. [ABSTRACT FROM AUTHOR]

Soil freeze depth variations greatly affect energy exchange, carbon exchange, ecosystem diversity, and the water cycle. Given the importance of these processes, obtaining freeze depth data over large scales is an important focus of research. This paper presents a simple empirical algorithm to estimate the maximum seasonally frozen depth (MSFD) of seasonally frozen ground (SFG) in snowy regions. First, the potential influences of driving factors on the MSFD variations were quantified in the baseline period (1981–2010) based on the 26 meteorological stations within and around the SFG region of Heilongjiang province. The three variables that contributed more than 10% to MSFD variations (i.e., air freezing index, annual mean snow depth, and snow cover days) were considered in the analysis. A simple multiple linear regression to estimate soil freeze depth was fitted (1981–2010) and verified (1975–1980 and 2011–2014) using ground station observations. Compared with the commonly used simplified Stefan solution, this multiple linear regression produced superior freeze depth estimations, with the mean absolute error and root mean square error of the station average reduced by over 20%. By utilizing this empirical algorithm and the ERA5-Land reanalysis dataset, the multi-year average MSFD (1981–2010) was 132 cm, ranging from 52 cm to 186 cm, and MSFD anomaly exhibited a significant decreasing trend, at a rate of −0.38 cm/decade or a net change of −28.14 cm from 1950–2021. This study provided a practical approach to model the soil freeze depth of SFG over a large scale in snowy regions and emphasized the importance of considering snow cover variables in analyzing and estimating soil freeze depth. [ABSTRACT FROM AUTHOR]

GaoFen 7 (GF-7) is China's first submeter high-resolution stereo mapping satellite with dual-linear-array cameras and a laser altimeter system onboard for high-precision mapping. To further take advantage of the very high elevation accuracy of laser altimetry data and the high relative accuracy with stereo images, an innovative combined adjustment method for GF-7 stereo images with laser altimetry data is presented in this paper. In this method, two flexible and effective schemes were proposed to extract the elevation control point according to the registration of footprint images and stereo images and then utilized as vertical control in the block adjustment to improve the elevation accuracy without ground control points (GCPs). The validation experiments were conducted in Shandong, China, with different terrains. The results demonstrated that, after using the laser altimetry data, the root mean square error (RMSE) of elevation was dramatically improved from the original 2.15 m to 0.75 m, while the maximum elevation error was less than 1.6 m. Moreover, by integrating a few horizontal control points, the planar and elevation accuracy can be simultaneously improved. The results show that the method will be useful for reducing the need for field survey work and improving mapping efficiency. [ABSTRACT FROM AUTHOR]

[Objectives]This paper aimed to research on the residue behavior of emamectin benzoate and pyriproxyfen in field corn and evaluate the chronic dietary risk, so as to provide suggestions for the rational use of emamectin benzoate and pyriproxyfen on corn. [Methods]In accordance with good agricultural practices(GAP), the field trials of 12% microemulsion(3% emamectin benzoate+9% pyriproxyfen, ME)on corn were carried out across 12 regions of main corn production in China. The formulation of 12% ME was sprayed once at the dosage of 45 g·hm-2 during the incubation period of corn borer eggs, and the recommended pre-harvest interval(PHI)was 21 days. Meanwhile, a method for determination of emamectin benzoate and pyriproxyfen in corn was developed based on QuEChERS and high-performance liquid chromatography-tandem mass spectrometry(HPLC-MS/MS), which was applied to detect the residue levels in field corn samples, and the chronic dietary risk was assessed based on field trial results. [Results]At the spiked levels of 0.01, 0.05, 0.1 and 1 mg·kg-1, the mean recoveries of emamectin B1a and pyriproxyfen in fresh corn, corn kernels and corn straw samples were 87%-106%, with relative standard deviations(RSD)of 2.3%-7.5% and limits of quantification(LOQ)all being 0.01 mg·kg-1. In the fresh corn and corn kernel samples harvested at 21 and 28 days after application, the terminal residue levels of emamectin B1a benzoate were less than 0.011 mg·kg-1, which were lower than the maximum residue limit(MRL)of emamectin benzoate in corn in China(fresh corn:0.05 mg·kg-1; corn kernel:0.05 mg·kg-1), and the terminal residue levels of pyriproxyfen were less than 0.01 mg·kg-1(At present, the MRL of pyriproxyfen on corn had not been set in China). The chronic risk quotients of emamectin benzoate and pyriproxyfen were 78.4% and 5.8%, respectively, which were both lower than 100%, indicating a low risk to consumer's health. [Conclusions]Under the GAP conditions of applying 12% microemulsion(3% emamectin benzoate+9% pyriproxyfen)on corn, the recommended PHI of 21 days was safe. The paper could also offer a reference for China to formulate the MRL of pyriproxyfen on corn. [ABSTRACT FROM AUTHOR]

In this paper, we have modified the International Reference Ionosphere model 2016 (IRI2016) with the Global Navigation Satellite System total electron content data observation in China by adjusting the ionospheric index (IG12) for given location and time. The capability of the modified IRI2016 to reproduce the F2 layer critical frequency foF2 is validated for high/low solar activity conditions and disturbed geomagnetic conditions for the time period 2014–2017 over low‐latitude ionosonde station located at Sanya in China. The analysis shows that the modified IRI2016 better reproduced the variability of the observed foF2 versus time and seasons. Also, the modified IRI2016 foF2 prediction exhibits lower root mean square error and higher correlation coefficients (R) over different solar activity periods, and significantly reduces the average percentage deviations (△foF2(%)) under enhanced geomagnetic activity periods. Subsequently, the 24 hr ahead forecast foF2 map over China constructed by the combination of the modified IRI2016 and the eXtreme Gradient Boosting algorithm is presented for the first time. The promising performance of the modified IRI2016 indicates that this combination method may be an effective way to predict the ionospheric parameters, though further validations are needed in the future work. Key Points: The International Reference Ionosphere model 2016 (IRI2016) is modified with the Global Navigation Satellite System data by adjusting the ionospheric index for given location and time in ChinaThe modified IRI2016 improves the foF2 prediction for both high/low solar activity conditions and disturbed geomagnetic conditionsThe 24 hr ahead forecast foF2 map over China is constructed for the first time to our knowledge [ABSTRACT FROM AUTHOR]

Water quality prediction is a fundamental and necessary task for the prevention and management of water environment pollution. Due to the fluidity of water, different sections of the same river have similar trends in their water quality. The present water quality prediction methods cannot exploit the correlation between the water quality of each section to deeply capture information because they do not take into account how similar the water quality is between sections. In order to address this issue, this paper constructs a water quality prediction model based on multi-task deep learning, taking the chemical oxygen demand (COD) of the water environment of the Lanzhou portion of the Yellow River as the research object. The multiple sections of correlation are trained and learned in this model at the same time, and the water quality information of each section is shared while retaining their respective heterogeneity, and the hybrid model CNN-LSTM is used for better mining from local to full time series features of water quality information. In comparison to the current single-section water quality prediction, experiments have shown that the model's mean absolute error (MSE) and root mean square error (RMSE) of the predicted value of the model are decreased by 13.2% and 15.5%, respectively, and that it performs better in terms of time stability and generalization. [ABSTRACT FROM AUTHOR]

Different radiometer sensors have different frequencies, spatial resolutions, and time resolutions, which lead to inconsistencies in ice drift products retrieved by radiometer sensors. Based on the continuous maximum cross-correlation method, in this paper, we used China's FY-3 and HY-2 satellite radiometer data to generate sea ice drift products; we further evaluated the consistency between them and sea ice drift products retrieved from AMSR2 and SSMIS satellite radiometer data, which could help in future retrieval accuracies of more radiometer sea ice drift products. The results show that ice drift products with good reliability can be obtained by retrievals using 37 and 89 GHz channels of FY-3 and HY-2 radiometer bright temperature data. Compared with the buoy data, the root mean square errors (RMSEs) of the 37 GHz HY-2 sea ice drift product (at an interval of 6 days) were 1.40 cm/s and 7.31° for speed and direction, respectively, and the relative errors (REs) were 5.78% and 6.44%, respectively. The RMSEs of the 37 GHz FY-3 sea ice drift product were 0.77 cm/s and 6.49° for speed and direction, respectively, and the REs were 4.38% and 9.23%, respectively. Moreover, comparisons between sea ice drift vectors derived from AMSR2 and SSMIS satellites showed good quantitative agreement. [ABSTRACT FROM AUTHOR]

Clarifying the sources of the digital finance inclusive development gap helps profoundly understand the regional characteristics of inclusive digital finance and benefits and formulate and implement specific policies scientifically and reasonably. Based on the 2011–2020 "Peking University Digital Finance Inclusive Index," this study explores the regional disparity in digital finance inclusive development and its sources in the Yangtze River Delta economic cluster using the methods of the center of gravity shift, standard deviation ellipse, nested Theil index difference decomposition, and Kernel density. We found that inclusive digital finance shows a rising trend year by year, with evident heterogeneity and spatial agglomeration characteristics; interprovincial differences are the primary sources of the overall differences in inclusive digital finance in the Yangtze River Delta. The spatial effect of digital inclusion finance between the Yangtze River Delta regions has continuity. Because of the significant positive spatial correlation of digital inclusion finance between regions, digital inclusion finance in this region is vulnerable to potential shocks from neighboring regions. Moreover, with or without the spatial lag term, the level of inclusive digital finance in all regions of the Yangtze River Delta shows a leap forward. This paper looks at the regional gap of inclusive digital finance and its structural decomposition in the Yangtze River Delta city cluster from three perspectives: time trend, spatial structure, and dynamic evolution. This gives an empirical basis for the different kinds of digital finance inclusive development policies and a guide for making decisions to speed up the formation of a regional digital finance inclusive synergistic development path. [ABSTRACT FROM AUTHOR]

In 2022, as a result of the historically exceptional high temperatures that have been observed this summer in several parts of China, particularly in the province of Sichuan, residential demand for energy has increased. Up to 70% of Sichuan's electricity comes from hydropower, thus creating a sensible and practical reservoir scheduling plan is essential to maximizing reservoir power generating efficiency. However, classical optimization, such as back propagation (BP) neural network, does not take into account the correlation of samples in time while generating reservoir scheduling rules. We proposed a prediction model based on LSTM neural network coupled with wavelet transformation (WT-LSTM) to address the problem. In order to extract the reservoir scheduling rules, this paper first gathers the scheduling operation data from the Xiluodu hydropower station and creates a dataset. Next, it uses the feature of the time-series prediction model with the realization of a complex nonlinear mapping function, time-series learning capability, and high prediction accuracy. The results demonstrate that the time-series deep learning network has high learning capability for reservoir scheduling by comparing evaluation indexes such as root mean square error (RMSE), rank-sum ratio (RSR), and Nash–Sutcliffe efficiency (NSE). The WT-LSTM network model put forward in this research offers better prediction accuracy than conventional recurrent neural networks and serves as a reference base for scheduling decisions by learning previous scheduling data to produce outflow solutions, which has some theoretical and practical benefits. [ABSTRACT FROM AUTHOR]

Accurate prediction of PM2.5 concentration is one of the key tasks of air pollution assessment, early warning, and treatment. In this paper, four monitoring sites were arranged in Jiangbei New District of Nanjing City, China. The environmental parameters such as PM2.5/PM10 concentration, temperature, and humidity were monitored from January to February 2020. A gated recurrent unit (GRU) network based on the PM2.5 concentration prediction model was established to predict PM2.5 concentration. The mean relative error (MRE), root mean square error (RMSE), and Pearson correlation coefficient were selected as the evaluation criteria for the accuracy of the GRU model. The data set was divided into a training set, a test set and a validation set at a ratio of 7:2:1, and the GRU model was used to predict the hourly value of PM2.5 concentration in the next week. The prediction results show that the Pearson correlation coefficients between the predicted values and the monitored values of the four monitoring sites have reached more than 0.9, reflecting a strong correlation. The relative average errors are around 10%. The GRU model prediction of NJAU (Nanjing Agricultural University)-Pukou Campus Site is the most accurate, and the correlation coefficient, MRE, and RMSE are 0.970, 7.85%, and 9.6049, respectively, reflecting the good prediction performance of the model. Therefore, this research supports the prediction of air quality in different cities and regions, so people can take protective measures in advance and reduce the damage caused by air pollution to human bodies. [ABSTRACT FROM AUTHOR]

Though numerical wave models have been applied widely to significant wave height prediction, they consume massive computing memory and their accuracy needs to be further improved. In this paper, a two-dimensional (2D) significant wave height (SWH) prediction model is established for the South and East China Seas. The proposed model is trained by Wave Watch III (WW3) reanalysis data based on a convolutional neural network, the bidirectional long short-term memory and the attention mechanism (CNNBiLSTM-Attention). It adopts the convolutional neural network to extract spatial features of original wave height to reduce the redundant information input into the BiLSTM network. Meanwhile, the BiLSTM model is applied to fully extract the features of the associated information of time series data. Besides, the attention mechanism is used to assign probability weight to the output information of the BiLSTM layer units, and finally, a trainingmodel is constructed. Up to 24-h prediction experiments are conducted under normal and extreme conditions, respectively. Under the normal wave condition, for 3-, 6-, 12- and 24-h forecasting, the mean values of the correlation coefficients on the test set are 0.996, 0.991, 0.980, and 0.945, respectively. The corresponding mean values of the root mean square errors are measured at 0.063 m, 0.105 m, 0.172 m, and 0.281 m, respectively. Under the typhoon-forced extreme condition, the model based on CNN-BiLSTM-Attention is trained by typhooninduced SWH extracted from the WW3 reanalysis data. For 3-, 6-, 12- and 24-h forecasting, the mean values of correlation coefficients on the test set are respectively 0.993, 0.983, 0.958, and 0.921, and the averaged root mean square errors are 0.159 m, 0.257 m, 0.437 m, and 0.555 m, respectively. The model performs better than that trained by all the WW3 reanalysis data. The result suggests that the proposed algorithm can be applied to the 2D wave forecast with higher accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Sea surface temperature (SST) is closely related to global climate change, ocean ecosystem, and ocean disaster. Accurate prediction of SST is an urgent and challenging task. With a vast amount of ocean monitoring data are continually collected, data-driven methods for SST time-series prediction show promising results. However, they are limited by neglecting complex interactions between SST and other ocean environmental factors, such as air temperature and wind speed. This paper uses multi-factor time series SST data to propose a sequence-to-sequence network with two-module attention (TMA-Seq2seq) for long-term time series SST prediction. Specifically, TMASeq2seq is an LSTM-based encoder-decoder architecture facilitated by factorand temporal-attention modules and the input of multi-factor time series. It takes six-factor time series as the input, namely air temperature, air pressure, wind speed, wind direction, SST, and SST anomaly (SSTA). A factor attention module is first designed to adaptively learn the effect of different factors on SST, followed by an encoder to extract factor-attention weighted features as feature representations. And then, a temporal attention module is designed to adaptively select the hidden states of the encoder across all time steps to learn more robust temporal relationships. The decoder follows the temporalattentionmodule to decode the feature vector concatenated from the weighted features and original input feature. Finally, we use a fully-connect layer to map the feature into prediction results. With the two attention modules, our model effectively improves the prediction accuracy of SST since it can not only extract relevant factor features but also boost the long-term dependency. Extensive experiments on the datasets of China Coastal Sites (CCS) demonstrate that our proposed model outperforms other methods, reaching 98.29% in prediction accuracy (PACC) and 0.34 in root mean square error (RMSE). Moreover, SST prediction experiments in China's East, South, and Yellow Sea site data show that the proposed model has strong robustness and multi-site applicability. [ABSTRACT FROM AUTHOR]

Because the penetration depth of electromagnetic waves in forests is large in the longer wavelength band, most traditional forest height estimation methods are carried out using polarimetric interferometry synthetic aperture radar (PolInSAR) data of the L or P band, and the estimation method is a three-stage method based on the random volume over ground (RVoG) model. For X-band electromagnetic waves, the penetration depth of radar waves in forests is limited, so the traditional forest height estimation method is no longer applicable. In view of the above problems, in this paper we propose a new forest height estimation strategy for airborne X-band PolInSAR data. Firstly, the sub-view interferometric SAR pairs obtained via frequency segmentation (FS) in the Doppler domain are used to extend the polarimetric interferometry coherence coefficient (PolInCC) range of the original SAR image under different polarization states, so as to obtain the accurate ground phase. For the determination of the effective volume coherence coefficient (VCC), part of the fitting line of the extended-range PolInCC distribution that is intercepted by the fixed extinction coherence coefficient curve (FECCC) of the fixed range is averaged to obtain the accurate effective VCC. Finally, the high-precision forest canopy height in the X-band is estimated using the effective VCC with the ground phase removed in the look-up table (LUT). The effectiveness of the proposed method was verified using airborne-measured data obtained in Shaanxi Province, China. The comparison was carried out using different strategies, in which we substituted one step of the process with the conventional method. The results indicated that our new strategy could reduce the root mean square error (RMSE) of the predicted canopy height vastly to 1.02 m, with a lower estimation height error of 12.86%. [ABSTRACT FROM AUTHOR]

The parameters of hydrological models should be determined before applying those models to estimate or predict hydrological processes. The Xin'anjiang (XAJ) hydrological model is widely used throughout China. Since the prediction in ungauged basins (PUB) era, the regionalization of the XAJ model parameters has been a subject of intense focus; nevertheless, while many efforts have targeted parameters related to runoff yield using in-site data sets, classic regression has predominantly been applied. In this paper, we employed remotely sensed underlying surface data and a machine learning approach to establish models for estimating the runoff routing parameter, namely, CS, of the XAJ model. The study was conducted on 114 catchments from the Catchment Attributes and MEteorology for Large-sample Studies (CAMELS) data set, and the relationships between CS and various underlying surface characteristics were explored by a gradient-boosted regression tree (GBRT). The results showed that the drainage density, stream source density and area of the catchment were the three major factors with the most significant impact on CS. The best correlation coefficient (r), root mean square error (RMSE) and mean absolute error (MAE) between the GBRT-estimated and calibrated CS were 0.96, 0.06 and 0.04, respectively, verifying the good performance of GBRT in estimating CS. Although bias was noted between the GBRT-estimated and calibrated CS, runoff simulations using the GBRT-estimated CS could still achieve results comparable to those using the calibrated CS. Further validations based on two catchments in China confirmed the overall robustness and accuracy of simulating runoff processes using the GBRT-estimated CS. Our results confirm the following hypotheses: (1) with the help of large sample of catchments and associated remote sensing data, the ML-based approach can capture the nonstationary and nonlinear relationships between CS and the underlying surface characteristics and (2) CS estimated by ML from large samples has a robustness that can guarantee the overall performance of the XAJ mode. This study advances the methodology for quantitatively estimating the XAJ model parameters and can be extended to other parameters or other models. [ABSTRACT FROM AUTHOR]

The problem of global warming is getting more serious, and vehicle emission is the main cause. In recent years, the number of locomotives in China has been increasing at a rate of more than 20% per year, and the problem of automobile pollution is becoming more serious. The transportation industry is the main source of fossil fuel combustion and environmental pollution. Therefore, in this paper, we propose a multi-view deep neural network (MVDNN) to analyze the key factors affecting the fuel consumption of automobiles. The experiments show that the introduction of human input improves the prediction accuracy and the root mean square error (RMSE) achieves 0.993. In addition, this paper also finds that for drivers, driving habits, driving frequency, and safety awareness are the most important factors affecting the fuel consumption of vehicles by combining Lasso regression with MVDNN. Finally, by comparing the prediction accuracy of different experiments, relevant policy suggestions are made. [ABSTRACT FROM AUTHOR]

Solar irradiance data include temporal information and geospatial information, so solar irradiance prediction can be regarded as a spatiotemporal sequence prediction problem. However, at present, most of the research is based on time series prediction models, and the research studies on spatial-temporal series prediction models are relatively few. Therefore, it is necessary to integrate spatial-temporal information to construct a spatial-temporal sequence prediction model for research. In this paper, the spatial-temporal prediction model based on graph convolutional network (GCN) and long short-term memory network (LSTM) was established for short-term solar irradiance prediction. In this model, solar radiation observatories were modeled as undirected graphs, where each node corresponds to an observatory, and a GCN was used to capture spatial correlations between sites. For each node, temporal features were extracted by using a LSTM. In order to evaluate the prediction performance of this model, six solar radiation observatories located in the Xinjiang region of China were selected; together with widely used persistence model seasonal autoregressive integrated moving average and data-driven prediction models such as convolutional neural network, recurrent neural network, and LSTM, comparisons were made under different seasons and weather conditions. The experimental results show that the average root mean square error of the GCN-LSTM model at the six sites is 62.058 W / m 2 , which is reduced by 9.8%, 14.3%, 6.9%, and 3.3%, respectively, compared with other models; the average MAE is 25.376 W / m 2 , which is reduced by 27.7%, 26.5%, 20.1%, and 11%, respectively, compared with other models; the average R2 is 0.943, which is improved by 1.4%, 2.2%, 0.8%, and 0.4%, respectively, compared with other models. [ABSTRACT FROM AUTHOR]

Objective. Infectious diseases usually spread rapidly. This study aims to develop a model that can provide fine-grained early warnings of infectious diseases using real hospital data combined with disease transmission characteristics, weather, and other multi-source data. Methods. Based on daily data reported for infectious diseases collected from several large general hospitals in China between 2012 and 2020, seven common infectious diseases in medical institutions were screened and a multi self-regression deep (MSRD) neural network was constructed. Using a recurrent neural network as the basic structure, the model can effectively model the epidemiological trend of infectious diseases by considering the current influencing conditions while taking into account the historical development characteristics in time-series data. The fitting and prediction accuracy of the model were evaluated using mean absolute error (MAE) and root mean squared error. Results. The proposed approach is significantly better than the existing infectious disease dynamics model, susceptible-exposed-infected-removed (SEIR), as it addresses the concerns of difficult-to-obtain quantitative data such as latent population, overfitting of long time series, and considering only a single series of the number of sick people without considering the epidemiological characteristics of infectious diseases. We also compare certain machine learning methods in this study. Experimental results demonstrate that the proposed approach achieves an MAE of 0.6928 and 1.3782 for hand, foot, and mouth disease and influenza, respectively. Conclusion. The MRSD-based infectious disease prediction model proposed in this paper can provide daily and instantaneous updates and accurate predictions for epidemic trends. [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]

A method based on the radial basis function neural network (RBFNN) is developed to fast establish the tropospheric refractivity profile model. Parameters of the RBFNN include SPREAD, and the number of training samples is optimized. The actual measured data of meteorological station at Qingdao city in China are used as test data to evaluate the performance of RBFNN. The simulation results show that the root mean squared error (RMSE) has a minimum of 0.81 when SPREAD is 8.1. The simulated values agree well with the test data which is observed by using the sounding balloon method. Finally, the tropospheric refractivity profile model of a selected area is established by using two different simulation methods. This paper attempts to propose a method to fast establish the tropospheric refractivity profile model which provides an available method to correct the atmospheric refraction error in radar applications. [ABSTRACT FROM AUTHOR]

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Backgrounds: UAVs for crop protection hold significant potential for application in mountainous orchard areas in China. However, certain issues pertaining to UAV spraying need to be addressed for further technological advancement, aimed at enhancing crop protection efficiency and reducing pesticide usage. These challenges include the potential for droplet drift, limited capacity for pesticide solution. Consequently, efforts are required to overcome these limitations and optimize UAV spraying technology. Methods: In order to balance high deposition and low drift in plant protection UAV spraying, this study proposes a plant protection UAV spraying method. In order to study the operational effects of this spraying method, this study conducted a UAV spray and grid impact test to investigate the effects of different operational parameters on droplet deposition and drift. Meanwhile, a spray model was constructed using machine learning techniques to predict the spraying effect of this method. Results and discussion: This study investigated the droplet deposition rate and downwind drift rate on three types of citrus trees: traditional densely planted trees, dwarf trees, and hedged trees, considering different particle sizes and UAV flight altitudes. Analyzing the effect of increasing the grid on droplet coverage and deposition density for different tree forms. The findings demonstrated a significantly improved droplet deposition rate on dwarf and hedged citrus trees compared to traditional densely planted trees and adopting a fixed-height grid increased droplet coverage and deposition density for both the densely planted and trellised citrus trees, but had the opposite effect on dwarfed citrus trees. When using the grid system. Among the factors examined, the height of the sampling point exhibited the greatest influence on the droplet deposition rate, whereas UAV flight height and droplet particle size had no significant impact. The distance in relation to wind direction had the most substantial effect on droplet drift rate. In terms of predicting droplet drift rate, the BP neural network performed inadequately with a coefficient of determination of 0.88. Conversely, REGRESS, ELM, and RBFNN yielded similar and notably superior results with a coefficient of determination greater than 0.95. Notably, ELM demonstrated the smallest root mean square error. [ABSTRACT FROM AUTHOR]

Interferometric Synthetic Aperture Radar (InSAR) technology is an important method to generate digital surface model (DSM). The past studies on space-borne derived DSM most focused on the elevation correction, due to the relative low resolution of DSM product. As a large number of high-resolution satellite data emerge, the horizontal discrepancies are needed to be considered. This paper proposes a DSM block adjustment method with horizontal constraints, aimed at eliminating the horizontal errors that exist between multiple DSM scenes with overlaps, achieving high precision and consistency in both the horizontal and vertical dimensions. Using ICESat-2 ATL08 point clouds as absolute elevation control and a reference DSM for horizontal control, the adjustment equations are constructed based on the constraint of tie points and controls. The experiment selects 7 image pairs of China TH2-01 SAR satellite, corresponding ICESat-2 ATL08 point and AW3D30 as reference DEM. The block adjustment results show that the proposed method improves the absolute vertical accuracy from 3.78 m to 2.56 m and reduces the average horizontal standard deviation between the InSAR derived DSMs and the reference AW3D30 from 15.31 m to 9.08 m. [ABSTRACT FROM AUTHOR]

Improving urban carbon emission efficiency (CEE) is vital to achieving the goal of urban carbon neutrality. However, the synergistic configurational effect of multiple influencing factors on CEE is not clear. Taking the Yangtze River Economic Belt (YREB) as an example, this paper adopts the standard deviation ellipse and Dagum Gini coefficient method to investigate the spatiotemporal differences in urban CEE in the YREB, and using the fuzzy-set qualitative comparative analysis (fsQCA) method, it explores the configurational effect of CEE influencing factors from the system perspective. The main conclusions are as follows: first, the overall level of urban CEE in the YREB is low, with a certain polarization phenomenon. Second, the relative differences in urban CEE in the YREB show a fluctuating upward trend, and the regional differences mainly originate from the overlapping part between regions. Finally, the main CEE influencing factors do not act in isolation, they constitute a complex process of synergistic interaction, with complementary substitution and causal asymmetry. [ABSTRACT FROM AUTHOR]

Topographic variables derived from digital elevation models (DEM) are the most commonly used predictor in soil organic carbon (SOC) prediction. The predictability of these variates for the spatial heterogenity of SOC is influenced by the size of DEM resolution. This paper aimed to investigate the resolution effect of the topography at multiple DEM resolutions and select the most important predictors and the optimal resolution for SOC prediction in a large-scale and morphologically complex area. The study area, covering 15 600 km2, was located in a mountainous province in China. A total of 3901 soil samples and three machine learning algorithms including random forest, gradient boosted regression tree, and artificial neural network were used to construct the SOC predictive models at resolutions of 30, 90, 150, 210, 270, 330, and 390 m. Topographic factors were derived from the DEM with an original resolution of 30 m and were subsequently resampled to varying resolutions by using the bilinear interpolation algorithm. The importance of each variate in each predictive model was computed for the most important predictor selection, and the determination coefficient (R2) and Root Mean Square Error (RMSE) of each predictive model were computed for the accuracy evaluation. Comparative analysis on point-based topographic representation, the accuracy of predictive models, and the variable importance was conducted among different resolutions to investigate the resolution effect on the SOC prediction and to select the optimal resolution for this study area. The results showed that topography was the key factor influencing the SOC distribution in this large-scale area due to the region's mountainous nature, and the relative contribution of the topography to predict SOC distribution varied with DEM resolutions. Elevation was the most important topographic factor at all DEM resolutions. Accuracies of predictive models built on the three machine learning algorithms were all dependent on DEM resolution, indicating that DEM resolution had an important effect on SOC prediction. Overall, the random forest predictive models outperformed the other two algorithms, and its most accurate result was obtained at the 210-m resolution with an R2 of 0.25 and an RMSE of 4.77 g kg–1. In conclusion, we found that finer resolutions did not necessarily produce more accurate SOC predictions even in a large-scale and morphologically complex area. Therefore, investigating the resolution effect is suggested to select an optimal resolution for the SOC prediction in other regions characterized by similar geomorphological conditions as this study area. [ABSTRACT FROM AUTHOR]