Search

In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them. [ABSTRACT FROM AUTHOR]

The role of precursors' concentrations and meteorological conditions on the emerging ozone pollution problem in China has received wide attention, especially after the releasing of the Air Pollution Prevention Control and Action Plan (APPC) since 2013. With the decreasing trend of PM 2.5 nationwide, the effect of the strict control measures on increasing ozone variation has less been studied due to the challenge of complexity of nonlinear relationship among a number of factors on ozone formation. This paper evaluated the influence of both ozone precursors and meteorology on maximum daily average 8 h (MDA8) ozone at two urban sites and one rural site in Hebei province, China, from 2013 to 2017, by using a combined application of Kolmogorov-Zurbenko (KZ) filter and artificial neural network (ANN) model. Results showed that R2 was 0.80 between the measured and the simulated MDA8 ozone concentration when using meteorological factors and precursors' concentrations as input variables for ANN model. However, ANN model has limitation in estimating O 3 concentration peaks. The values of threat score (TS), probability of detection (POD) and false alarm rate (FAR) for MDA8 ozone concentration were 39%, 44% and 21%, respectively, throughout three studied sites in Hebei province. The annual average percentage change of precursor-related ozone was 0.67% from 2014 to 2017. Temperature, atmospheric pressure and boundary layer height were shown to account for 64% of the variability in long-term ozone levels. Ozone variation in Hebei province was reproduced mainly by meteorological parameters, and the contribution from precursors' concentration was smaller during the years when the APPC was implemented. [Display omitted] • Ozone level was estimated based on precursors' level and meteorological factors. • The ambient ozone concentration estimated by ANN model was acceptable. • Meteorology dominates the ozone variation in 2013–2017 in Hebei province. [ABSTRACT FROM AUTHOR]

Cellular automata (CA) have been increasingly used to simulate complex urban systems. Empirical data can be used to calibrate CA models so that realistic urban patterns can be generated. Traditionally, the calibration procedure employs linear regression methods, e.g., multicriteria evaluation. However, the evolution of urban systems often manifests the complexity of non-linear features, for which the linear transition rules are insufficient. This paper proposes to use the kernel-based learning techniques to acquire non-linear transition rules for CA. The kernel-based approach maps the original data vectors to an implicit high-dimensional feature space, through which complex non-linear problems are translated into simple linear problems. Compared with a widely used non-linear method, neural network, the kernel method is more mathematically “transparent” and therefore the results are easier to be analyzed. A case study of simulating the expansion of Guangzhou, a fast growing city in China, shows that the kernel-based CA even achieves a slightly higher accuracy than a neural-network-based CA. [Copyright &y& Elsevier]

Abstract: This paper compares the predictive performance of ARIMA, artificial neural network and the linear combination models for forecasting wheat price in Chinese market. Empirical results show that the combined model can improve the forecasting performance significantly in contrast with its counterparts in terms of the error evaluation measurements. However, as far as turning points and profit criterions are concerned, the ANN model is best as well as at capturing a significant number of turning points. The results are conflicting when implementing dissimilar forecasting criteria (the quantitative and the turning points measurements) to evaluate the performance of three models. The ANN model is overall the best model, and can be used as an alternative method to model Chinese future food grain price. [Copyright &y& Elsevier]

Abstract: Harmful algal blooms, which are considered a serious environmental problem nowadays, occur in coastal waters in many parts of the world. They cause acute ecological damage and ensuing economic losses, due to fish kills and shellfish poisoning as well as public health threats posed by toxic blooms. Recently, data-driven models including machine-learning (ML) techniques have been employed to mimic dynamics of algal blooms. One of the most important steps in the application of a ML technique is the selection of significant model input variables. In the present paper, we use two extensively used ML techniques, artificial neural networks (ANN) and genetic programming (GP) for selecting the significant input variables. The efficacy of these techniques is first demonstrated on a test problem with known dependence and then they are applied to a real-world case study of water quality data from Tolo Harbour, Hong Kong. These ML techniques overcome some of the limitations of the currently used techniques for input variable selection, a review of which is also presented. The interpretation of the weights of the trained ANN and the GP evolved equations demonstrate their ability to identify the ecologically significant variables precisely. The significant variables suggested by the ML techniques also indicate chlorophyll-a (Chl-a) itself to be the most significant input in predicting the algal blooms, suggesting an auto-regressive nature or persistence in the algal bloom dynamics, which may be related to the long flushing time in the semi-enclosed coastal waters. The study also confirms the previous understanding that the algal blooms in coastal waters of Hong Kong often occur with a life cycle of the order of 1–2 weeks. [Copyright &y& Elsevier]

A high-dimensional dataset was built with time-series data of vegetation indexes derived from a Terra-Moderate Resolution Imaging Spectroradiometer (MODIS) sensor used for land use/cover classification. The self-organizing map (SOM) neural network technique can reduce the dimensionality of high-dimensional data, yet keep the same topological characters in the low-dimension space after dimension reduction. In this paper, we first employed the SOM neural network technique to classify land cover types using a 17-dimensional dataset that was generated from 16-day interval MODIS Enhanced Vegetation Index (EVI) data with a spatial resolution of 500 m in eastern China during the growing period of plants. Then, we defined an unlabelled class of neuron. Pixels matched to this type of neuron were regarded as unclassified land cover types, so that we could remove the poorly classified areas. Finally, the classification results were compared with those of the maximum likelihood classification (MLC) method. Comparison showed that the accuracy of the former exceeded that of the latter in classifying a high-dimensional dataset. [ABSTRACT FROM AUTHOR]

Abstract: Operationally AVHRR and TM/TM+ data were used and a supervised maximum likelihood classification (MLH) was applied to depict land use changes in Beijing, providing basic maps for planning and development. With rapid growth of the city these are helpful to deal with higher resolution data, whereas new classification algorithms produce land use maps more accurate. In the paper, new sensor ASTER data and the Kohonen self-organized neural network feature map (KSOM) were tested. The TSOM classified 7% more accurately than the maximum likelihood algorithm in general, and 50% more accurately for the classes ‘residential area’ and ‘roads’. The results suggest that ASTER data and the Kohonen self-organized neural network classification can be used as an alternative data and method in a land use update operational system. [Copyright &y& Elsevier]

Using the measured data on no-flow events in the Lower Yellow River since 1972, this paper presents an approach to describe the no-flow status in terms of a comprehensive indicator. The severity levels of no-flow events are identified by cluster analysis. Furthermore, the relation between severity levels and incoming water from upstream and its variance is well established with a BP-typed Artificial Neural Network (ANN), which is helpful to identify the complex response of the severity level to flow characteristics. The availability of the approach for quantitative description and prediction of no-flow events is discussed through comparisons between predicted and measured results in the Lower Yellow River. [ABSTRACT FROM AUTHOR]

This paper introduces the TERT-IV prototype developed by Tianjin University. The application of the TERT-IV system to measurement parameters of two-phase flow has been studied. The methods of analyzing measured data of ERT system are presented and applied to identify flow regimes and estimate void fraction. For the several typical flow regimes, the methods of principal component analysis and artificial neural network to identify the two-phase flow regimes is presented, and that is proved to have higher recognition rate by experimental test. For the different phase distribution on a pipe cross-section, the methods of relative changes summation and polynomial regression are used to estimate void fraction, and are proved to be possible by comparing the results of simulation calculation to the analytic results of experimental measured data.The research results show that the method is feasible using feature extraction and analysis data to measure the parameters of two-phase flow under the different flow conditions, and prove that it is possible to monitor on-line the transportation process of air/water two-phase flow using ERT system. [Copyright &y& Elsevier]

In recent years, research on intelligent systems is becoming more and more popular in academe. Intelligent systems research mainly involves the field of artificial intelligence. There are many research groups engaged in the research of intelligent systems in the world, and a variety of achievements have been made. In this paper, the main research institutions in China as well as their main research topics are introduced. [ABSTRACT FROM AUTHOR]

In Hong Kong, the annual traffic census report is published in the middle of the year and used to present the results of traffic volume recorded at the automatic traffic counter stations. The type of traffic volume data being widely used is the annual average daily traffic (AADT), which is estimated on the basis of the daily flows by 12 months in the whole surveyed year. In this paper, time series, neural network, nonparametric regression, and Gaussian maximum likelihood (GML) methods were adapted to develop four models for short-term prediction of the daily traffic flows by day of week and by month, as well as the AADT for the whole current year. The historical data (1994–1998) and available current-year data for 1999 partial daily flows are the input data used for model development. The results of the four models were compared with the real data for validation. The daily flows estimated by the four models were used to calculate the AADT for the current year of 1999. Based on the comparison results, the GML model appears to be the most promising and robust of these four models for extensive applications to provide the short-term traffic forecasting database for the whole territory of Hong Kong. [ABSTRACT FROM AUTHOR]

The average annual daily traffic (AADT) volumes can be estimated by using a short period count of less than twenty-four hour duration. In this paper, the neural network method is adopted for the estimation of AADT from short period counts and for the determination of the most appropriate length of counts. A case study is carried out by analysing data at thirteen locations on trunk roads and primary roads in urban area of Hong Kong. The estimation accuracy is also compared with the one obtained by regression analysis approach. The results show that the neural network approach consistently performed better than the regression analysis approach. [ABSTRACT FROM AUTHOR]

The accurate and timely estimation of regional crop biomass at different growth stages is of great importance in guiding crop management decision making. The recent availability of long time series of remote sensing data offers opportunities for crop monitoring. In this paper, four machine learning models, namely random forest (RF), support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting (XGBoost) were adopted to estimate the seasonal corn biomass based on field observation data and moderate resolution imaging spectroradiometer (MODIS) reflectance data from 2012 to 2019 in the middle reaches of the Heihe River basin, China. Nine variables were selected with the forward feature selection approach from among twenty-seven variables potentially influencing corn biomass: soil-adjusted total vegetation index (SATVI), green ratio vegetation index (GRVI), Nadir_B7 (2105–2155 nm), Nadir_B6 (1628–1652 nm), land surface water index (LSWI), normalized difference vegetation index (NDVI), Nadir_B4 (545–565 nm), and Nadir_B3 (459–479 nm). The results indicated that the corn biomass was suitably estimated (the coefficient of determination (R2) was between 0.72 and 0.78) with the four machine learning models. The XGBoost model performed better than the other three models (R2 = 0.78, root mean squared error (RMSE) = 2.86 t/ha and mean absolute error (MAE) = 1.86 t/ha). Moreover, the RF model was an effective method (R2 = 0.77, RMSE = 2.91 t/ha and MAE = 1.91 t/ha), with a performance comparable to that of the XGBoost model. This study provides a reference for estimating crop biomass from MOD43A4 datasets. In addition, the research demonstrates the potential of machine learning techniques to achieve a relatively accurate estimation of daily corn biomass at a large scale. [ABSTRACT FROM AUTHOR]

This paper develops a rigorous and advanced data-driven model to describe, analyze, and forecast the global crude oil demand. The study deploys a hybrid approach of artificial intelligence techniques, namely, the genetic-algorithm, neural-network, and data-mining approach for time-series models (GANNATS). The GANNATS was developed and applied to two country cases, including one for a high oil producer (Saudi Arabia) and one for a high oil consumer (China), to develop crude oil demand forecasts. The input variables of the neural network models include gross domestic product (GDP), the country's population, oil prices, gas prices, and transport data, in addition to transformed variables and functional links. The artificial intelligence predictive models of oil demand were successfully developed, trained, validated, and tested using historical oil-market data, yielding excellent oil demand predictions. The performance of the intelligent models for Saudi Arabia and China was examined using rigorous indicators of generalizability, predictability, and accuracy. The GANNATS forecasting models show that the crude oil demand for both Saudi Arabia and China will continue to increase over the forecast period but with a mildly declining growth, particularly for Saudi Arabia. This decreasing growth in the demand for oil can be attributed to increased energy efficiency, fuel switching, conversion of power plants from crude oil to gas-based plants, and increased utilization of renewable energy, such as solar and wind for electricity generation and water desalination. In this study, the feature engineering of variables selection techniques has been applied to identify and understand significant factors that impact and drive the crude oil demand. The proposed GANNATS methodology optimizes and upgrades the conventional process of developing oil demand forecasts. It also improves and enhances the predictability and accuracy of the current oil demand forecasting models. • Developed GANNATS models for modeling, analyzing and predicting the crude oil demand. • Identified and discussed the influential factors driving the crude oil demand of Saudi Arabia and China. • Predicted crude oil demand for Saudi Arabia and China for the short-term outlook. • Provided a guide for AI/ML generalization attributes. • Provided golden rules and tips for modeling GANNATS. [ABSTRACT FROM AUTHOR]

The energy consumption pattern dominated by traditional fossil energy has led to global energy resource constraints and the deterioration of the ecological environment. These challenges have become a major issue all over the world. At present, the Chinese government aims to significantly reduce the fossil energy consumption contribution in the terminal energy consumption. The development of renewable energy in the terminal energy and energy conversion links has significantly increased the proportion of clean low-carbon energy. In order to accurately get the proportion of renewable energy terminal power consumption, firstly, this paper selects a primary influencing-factors set including the gross GDP, fixed investment in renewable energy industry, total length of cross-provincial and cross-regional high-voltage transmission lines, etc. as influencing factors of China's electricity consumption fraction produced by renewable energy based on a multitude of papers. Secondly, from the perspective of signal decomposition, the data inevitably has a lot of interference and noise. This paper uses the empirical mode decomposition (EMD) algorithm to reduce the degree of signal distortion and decomposes the signal into natural modes including several intrinsic mode functions (IMFs) and a residual term (Res); afterwards, a new extreme learning machine (ELM) forecasting model optimized by an Inverse Square Root Linear Units (ISRLU) activation function is proposed, and the ISRLU function is used to replace the implicit layer activation function in the original ELM algorithm. Then, a new bacterial foraging algorithm (BFOA) is applied to optimize the parameters of the optimized ELM forecasting model. After multiple learning and training operations, the optimal parameters are obtained. Finally, we superimpose the output of each IMF and Res training task to get the amount of China's power consumption produced by renewable energy. Some statistical indicators including root mean squard error (RMSE) are applied to compare the accuracy of several intelligent machine forecasting algorithms. We prove that the proposed forecasting model has higher prediction accuracy and achieves faster training speed by an empirical analysis. Finally, the proposed combined forecasting algorithm is applied to predict China's renewable energy terminal power consumption from 2018 to 2030. According to the forecasting results, it is found that China's renewable energy terminal power consumption shows a gradual growth trend, and will exceeded 3300 billion kWh in 2030, which will represent a renewable energy terminal power ratio of about 38% in 2030. [ABSTRACT FROM AUTHOR]

• An evaluation model of soil quality in arid area BP - ANN based was established. • The model combined heavy metals and nutrients in soil has high accuracy. • Environmental controlling factors of soil quality have regional differences. Soil quality evaluation is an effective way to improve ecological environment quality of soil and to perfect management system as well as keep its productivity of the soil sustainable. However, in arid areas, the comprehensive study of soil quality has been paid little attention. This paper aims to classify and evaluate comprehensive soil quality which combined heavy metal contamination with soil nutrients in the arid area, and to explore the natural environmental controlling factors of soil quality under regional differences. Taking Hexi area, a typical arid area in northwest China, as the study area, the comprehensive evaluation model of soil quality based on back propagation artificial neural network (BP - ANN) was proposed. The results showed that the accuracies of the validated models were both more than 97 %. The soil quality in Hexi area was divided into six classes: IA, IB, IC, IIA, IIB, IIC (The number (I and II) represents the degree of heavy metal pollution, the larger the number, the higher the pollution degree; the letter (A, B, and C) represents the nutrient level, the latter the letter, the more barren the nutrient). Most of the samples were classified as IB and IC, indicating that the soil quality was good with mild heavy metal contamination and poorer nutrients. Group analysis was used to explore the impact of natural environmental factors on soil quality under different environmental characteristics through linear regression modeling. The results showed that elevation, annual mean cumulative precipitation, slope and topographic wetness index were the environmental controlling factors of the soil quality for all samples. Besides, the other important factors affecting soil quality in group 1 were: annual mean temperature and soil type. For group 2 it was LUCC (Land Use Cover Change). This study is of great significance to classify and define the soil quality, to maintain and improve agricultural production and soil ecological health in arid areas. [ABSTRACT FROM AUTHOR]

The aim of this paper is the generation of a time-series based statistical data-driven procedure in order to track an outbreak. At first are used univariate time series models in order to predict the evolution of the reported cases. Moreover, are considered combinations of the models in order to provide more accurate and robust results. Additionally, statistical probability distributions are considered in order to generate future scenarios. Final step is the build and use of an epidemiological model (tSIR) and the calculation of an epidemiological ratio (R 0) for estimating the termination of the outbreak. The time series models include Exponential Smoothing and ARIMA approaches from the classical models, also Feed-Forward Artificial Neural Networks and Multivariate Adaptive Regression Splines from the machine learning toolbox. Combinations include simple mean, Newbolt-Granger and Bates-Granger approaches. Finally, the tSIR model and the R 0 ratio are used for estimating the spread and the reversion of the pandemic. The suggested procedure is used to track the COVID-19 epidemic in Greece. This epidemic has appeared in China in December 2019 and has been widespread since then to all over the world. Greece is the center of this empirical study as is considered an early successful paradigm of resistance against the virus. [ABSTRACT FROM AUTHOR]

The accurate determination of methane adsorption isotherms in coals is crucial for both the evaluation of underground coalbed methane (CBM) reserves and design of development strategies for enhancing CBM recovery. However, the experimental measurement of high-pressure methane adsorption isotherms is extremely tedious and time-consuming. This paper proposed the use of an ensemble machine learning (ML) method, namely the gradient boosting decision tree (GBDT), in order to accurately estimate methane adsorption isotherms based on coal properties in the Qinshui basin, China. The GBDT method was trained to correlate the adsorption amount with coal properties (ash, fixed carbon, moisture, vitrinite, and vitrinite reflectance) and experimental conditions (pressure, equilibrium moisture, and temperature). The results show that the estimated adsorption amounts agree well with the experimental ones, which prove the accuracy and robustness of the GBDT method. A comparison of the GBDT with two commonly used ML methods, namely the artificial neural network (ANN) and support vector machine (SVM), confirms the superiority of GBDT in terms of generalization capability and robustness. Furthermore, relative importance scanning and univariate analysis based on the constructed GBDT model were conducted, which showed that the fixed carbon and ash contents are primary factors that significantly affect the adsorption isotherms for the coal samples in this study. [ABSTRACT FROM AUTHOR]

The purpose of this study is to produce a landslide susceptibility map of Southeastern Helong City, Jilin Province, Northeastern China. According to the geological hazard survey (1:50,000) project of Helong city, a total of 83 landslides were mapped in the study area. The slope unit, which is classified based on the curvature watershed method, is selected as the mapping unit. Based on field investigations and previous studies, three groups of influencing Factors—Lithological factors, topographic factors, and geological environment factors (including ten influencing factors)—are selected as the influencing factors. Artificial neural networks (ANN's) and support vector machines (SVM's) are introduced to build the landslide susceptibility model. Five-fold cross-validation, the receiver operating characteristic curve, and statistical parameters are used to optimize model. The results show that the SVM model is the optimal model. The landslide susceptibility maps produced using the SVM model are classified into five grades—very high, high, moderate, low, and very low—and the areas of the five grades were 127.43, 151.60, 198.77, 491.19, and 506.91 km2, respectively. The very high and high susceptibility areas included 79.52% of the total landslides, demonstrating that the landslide susceptibility map produced in this paper is reasonable. Consequently, this study can serve as a guide for landslide prevention and for future land planning in the southeast of Helong city. [ABSTRACT FROM AUTHOR]

The Fuel Cell Vehicles are going to be introduced in domestic cities of China, which will require urban Hydrogen Refueling Stations (HRS). Such urban refueling center would be a public concern given their location in the congested area and the potential hydrogen release and fire risk. Risk analysis of possible fire scenarios is an efficient approach to identify, evaluate, and mitigate the risk from such hydrogen fire accidents. However, due to lack of availability of data, there still exists high parametric uncertainty in the scenario envisaging risk analysis. It is crucial to minimize this parametric uncertainty to have robust hydrogen fire risk analysis. If minimizing the corresponding uncertainty, traditional procedure could bring much computational intensity. This paper proposes a robustly integrated procedure of the fire risk analysis for the urban HRS to reduce the uncertainty and the computational intensity. This newly proposed procedure integrates the Bayesian Regularization Artificial Neural Network (BRANN)-based non-intrusive method with the consequence modeling and statistical approaches. A case study is conducted to demonstrate the scenario-related parametric uncertainty effect and the feasibility of the procedure. The results indicate 300 simulation inputs are the optimal trade-off between the BRANN model's generalization capacity and computational intensity. With such number of simulations, the BRANN model could achieve the R 2 = 0.98. In addition, the proposed procedure could reduce the parametric uncertainty and computation cost by 97% and 99%, respectively. [ABSTRACT FROM AUTHOR]

This study is meant to investigate the main driving factors of energy consumption structure (ECS) in China and construct a hybrid prediction model with higher accuracy. In this paper, Logarithmic Mean Divisia Index (LMDI) is applied to study the factors of energy consumption structure of China covering 1980 to 2016 and calculate the contribution of each factor. The factors that have large contribution rate are selected as the main factors of energy consumption structure to simplify prediction model. And then, the original data series of energy consumption structure and main factors are decomposed into different components by empirical mode decomposition (EMD) model to deal with the intrinsic complexity and irregularity of sequences. Finally, the components are used as input data to construct the prediction model, least square support vector machine (LSSVM), the coefficients of which are optimized by the particle swarm optimization (PSO) algorithm. The results show that prediction error of EMD-PSOLSSVM model is significantly lower than benchmark models of grey model neural network and PSOLSSVM model. The constructed model fully exploits the advantages of each algorithm of the hybrid model and improves the prediction accuracy of energy consumption structure. Image 1 • The energy consumption structure in China is decomposed for 1980–2016. • The empirical mode decomposition is applied to decompose factors. • A hybrid prediction model is constructed to forecast energy consumption structure. • Income is dominant force of energy consumption structure. • The accuracy of hybrid model is far higher than benchmark models. [ABSTRACT FROM AUTHOR]

Land use change (LUC) exhibits obvious spatio-temporal dependency. Previous cellular automata (CA)-based methods usually treated the LUC dynamics as Markov processes and proposed a series of CA-Markov models, which however, were intrinsically unable to capture the long-term temporal dependency. Meanwhile, such models used only numerical proportion of neighboring land use (LU) types to represent neighborhood effects of LUC, which inevitably neglected the complicated spatial heterogeneity and thus caused inaccurate simulation results. To address these problems, this paper presents a novel CA model integrated with deep learning (DL) techniques to model spatio-temporal LUC dynamics. Our DL-CA model firstly uses a convolutional neural network to capture latent spatial features for complete representation of neighborhood effects. A recurrent neural network then extracts historical information of LUC from time-series land use maps. A random forest is appended as binary change predictor to avoid the imbalanced sample problem during model training. Land use data collected from 2000 to 2014 of the Dongguan City, China were used to verify our proposed DL-CA model. The input data from 2000 to 2009 were used for model training, the 2010 data for model validation, and the data collected from 2011 to 2014 were used for model evaluation. In addition, four traditional CA models of multilayer perceptron (MLP)-CA, support vector machine (SVM)-CA, logistic regression (LR)-CA and random forest (RF)-CA were also developed for accuracy comparisons. The simulation results demonstrate that the proposed DL-CA model accurately captures long-term spatio-temporal dependency for more accurate LUC prediction results. The DL-CA model raised prediction accuracy by 9.3%–11.67% in 2011–2014 in contrast to traditional CA models. • A novel CA model is integrated with deep learning to model the dynamics of LUC. • LUC is treated as a long-term process and the temporal dependency is modeled by RNN. • For the spatial dependency in LUC, CNN is built to learn the latent spatial features. • RF is used as bootstrap to avoid imbalanced sampling during CNN-RNN model training. [ABSTRACT FROM AUTHOR]

Image classification is a fundamental task in remote sensing image processing. In recent years, deep convolutional neural networks (DCNNs) have experienced significant breakthroughs in natural image recognition. The remote sensing field, however, is still lacking a large-scale benchmark similar to ImageNet. In this paper, we propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsourced data. Using crowdsourced data, such as Open Street Map (OSM) data, ground objects in remote sensing images can be annotated effectively using points of interest, vector data from OSM, or other crowdsourced data. These annotated images can, then, be used in remote sensing image classification tasks. Based on this method, we construct a worldwide large-scale benchmark for remote sensing image classification. This benchmark has large-scale geographical distribution and large total image number. It contains six categories with 35 sub-classes of more than 24,000 images of size 256 × 256 pixels. This classification system of ground objects is defined according to the national standard of land-use classification in China and is inspired by the hierarchy mechanism of ImageNet. Finally, we conduct numerous experiments to compare RSI-CB with the SAT-4, SAT-6, and UC-Merced data sets. The experiments show that RSI-CB is more suitable as a benchmark for remote sensing image classification tasks than other benchmarks in the big data era and has many potential applications. [ABSTRACT FROM AUTHOR]

How to acquire landslide disaster information quickly and accurately has become the focus and difficulty of disaster prevention and relief by remote sensing. Landslide disasters are generally featured by sudden occurrence, proposing high demand for emergency data acquisition. The low-altitude Unmanned Aerial Vehicle (UAV) remote sensing technology is widely applied to acquire landslide disaster data, due to its convenience, high efficiency, and ability to fly at low altitude under cloud. However, the spectrum information of UAV images is generally deficient and manual interpretation is difficult for meeting the need of quick acquisition of emergency data. Based on this, UAV images of high-occurrence areas of landslide disaster in Wenchuan County and Baoxing County in Sichuan Province, China were selected for research in the paper. Firstly, the acquired UAV images were pre-processed to generate orthoimages. Subsequently, multi-resolution segmentation was carried out to obtain image objects, and the barycenter of each object was calculated to generate a landslide sample database (including positive and negative samples) for deep learning. Next, four landslide feature models of deep learning and transfer learning, namely Histograms of Oriented Gradients (HOG), Bag of Visual Word (BOVW), Convolutional Neural Network (CNN), and Transfer Learning (TL) were compared, and it was found that the TL model possesses the best feature extraction effect, so a landslide extraction method based on the TL model and object-oriented image analysis (TLOEL) was proposed; finally, the TLOEL method was compared with the object-oriented nearest neighbor classification (NNC) method. The research results show that the accuracy of the TLOEL method is higher than the NNC method, which can not only achieve the edge extraction of large landslides, but also detect and extract middle and small landslides accurately that are scatteredly distributed. [ABSTRACT FROM AUTHOR]

• CNNs are considered for dealing with the flood susceptibility mapping task. • Two different CNN frameworks of classification and feature extraction are presented. • Three data presentation forms are designed for the proposed CNN frameworks. • Reliable flood susceptibility maps can be obtained by using the proposed CNNs. • Prediction performance of SVM can be improved using the CNNs for feature extraction. Flood is a very destructive natural disaster in the world, which seriously threatens the safety of human life and property. In this paper, the most popular convolutional neural network (CNN) is introduced to assess flood susceptibility in Shangyou County, China. The main contributions of this study are summarized as follows. First, the CNN technique is used for flood susceptibility mapping through two different CNN classification and feature extraction frameworks. Second, three data presentation methods are designed in the CNN architecture to fit the two proposed frameworks. To construct the proposed CNN-based methods, 13 flood triggering factors related to historical flood events in the study area were prepared. The performance of these CNN-based methods was evaluated using several objective criteria in comparison to the conventional support vector machine (SVM) classifier. Experiments results demonstrate that all the CNN-based methods can produce more reliable and practical flood susceptibility maps. For example, the proposed CNN-based classifiers were 0.022–0.054 higher than SVM in terms of area under the curve (AUC). In addition, in the classification process, CNN-based feature extraction can effectively improve the prediction capability of SVM by 0.021–0.051 in terms of AUC. Therefore, the proposed CNN frameworks can help mitigate and manage floods. [ABSTRACT FROM AUTHOR]

This paper aims at studying the data-driven short-term provincial load forecasting (STLF) problem via an in-depth exploration of benefits brought by the feature engineering and model selection. Three core issues regarding model selections, feature selections, and feature encoding mechanism selections are deeply investigated. The candidate models are grouped into three types: the time series model, classical regression models, and the deep learning models. Three categories of features, historical loads, calendar effects, and weather factors, are considered and utilized in various encoding mechanisms. In experimental studies, an hourly provincial load dataset from Jiangsu Province in China and the corresponding weather records are utilized. The experiments are extensively performed in three parts according to model types. A time series model is conducted individually and the greedy forward wrapper-based feature selections (GFW-FS) are separately performed in six classical regression models to determine suitable encoded features. Deep learning approaches for developing STLF models are also considered. A deep neural network (DNN) model considering selected features of shallow neural networks (SNN) is developed. Meanwhile, a novel convolutional neural network (CNN) based model using GFW-FS is constructed. Through a comparative error analysis of the test set, the intrinsic linear nature among extracted features and the target in the 24-h-ahead provincial STLF problem is discovered. Feature effects are also evaluated. Data-driven models and their considered features, which are more effective to the STLF problem, are reported. • A short-term provincial load forecasting problem is studied via an in-depth analytics of data-driven models and developed features. • Classical machine learning and recent deep learning methods are applied to develop short-term provincial load forecasting models. • A greedy forward wrapper-based feature selection framework is developed to construct effective features for forecasting models. • Extensive computational experiments are conducted to explore best performed modeling methods and valuable features in the forecasting. [ABSTRACT FROM AUTHOR]

• The acoustic environment of a mountainous city is various from that of a plain city. • A conventional model is optimized by considering road gradient characteristics. • Roadway gradient should be strictly controlled during traffic noise management. • Multilayer feedforward artificial neural network is proposed to achieve nonlinear problem analysis. • Artificial neural network is the most efficient traffic noise predictive method. Different regions have established traffic noise prediction models to adapt to their particular environmental characteristics. This paper aimed to develop a traffic noise prediction model for mountainous cities. In China, the traffic noise prediction model HJ 2.4-2009, which itself is based on the sound pressure level corrected for roadway gradients (RGs), has been receiving widespread acceptance. On the basis of the model in HJ 2.4-2009, the RG correction coefficient was proposed to modify the original model and a per-vehicle noise prediction model was built using a multilayer feedforward artificial neural network (ANN) model. The data collected from a municipal road of a hilly city, Chongqing, was used to train and validate the ANN model. The predictor variables comprised the per-vehicle noise value, vehicle type, vehicle velocity, and roadway gradient. The results showed that the modified HJ 2.4-2009 model incorporating the gradient correction coefficient achieved a significantly higher R2 for mountainous cities than the original model. Besides, the ANN-based noise prediction model achieved considerable accuracy improvement over the empirical predictive equations. [ABSTRACT FROM AUTHOR]

• Multi-model forecast method of average wind speed and turbulent standard deviation. • Adaptive application of one-dimensional convolutional neural network. • Creative probabilistic wind speed forecast work based on turbulent standard deviation. • Demand-orientated case studies for 4 h ahead wind speed prediction of 16 steps. Accurate wind speed forecast can provide important information for power system dispatching. Many studies focus on this topic over the last decades, but it's consistently a tough issue due to the intense uncertainty of wind. In physical perspective, wind speed consists of average component and turbulent component. Therefore, oriented to actual demand and improve the forecast precision, this paper develops a novel data-driven method to realize short-term combination forecasts of average wind speed and wind turbulent standard deviation. According to atmospheric boundary layer theory and correlation analysis of the two prediction targets, their time-delay items are combined as the model input features. One-dimensional convolutional neural network is innovatively applied for this work to excavate the timing coupled information in data. Well-performed models can be established after adequate training and validation. Inspired by Pauta criterion, adaptive parameter named as "turbulent standard deviation multiplicator" is defined, which is the specific value of predicted average wind speed error and wind turbulent standard deviation. It is decided as the medium to extend the study to probabilistic framework. Based on its quantile analysis, the statistical significance of the parameter is verified and the prediction results can be integrated to achieve 4 h ahead probabilistic wind speed forecasts. Actual data from China wind farm is utilized to execute the case experiments. Superior performances indicate the feasibility and effectiveness of proposed method and the uncertainties of wind are better learned. [ABSTRACT FROM AUTHOR]

Background: The probability of heart failure during the perioperative period is 2% on average and it is as high as 17% when accompanied by cardiovascular diseases in China. It has been the most significant cause of postoperative death of patients. However, the patient is managed by the flow of information during the operation, but a lot of clinical information can make it difficult for medical staff to identify the information relevant to patient care. There are major practical and technical barriers to understand perioperative complications.Methods: In this work, we present three machine learning methods to estimate risks of heart failure, which extract intraoperative vital signs monitoring data into different modal representations (statistical learning representation, text learning representation, image learning representation). Firstly, we extracted features of vital signs monitoring data of surgical patients by statistical analysis. Secondly, the vital signs data is converted into text information by Piecewise Approximate Aggregation (PAA) and Symbolic Aggregate Approximation (SAX), then Latent Dirichlet Allocation (LDA) model is used to extract text topics of patients for heart failure prediction. Thirdly, the vital sign monitoring time series data of the surgical patient is converted into a grid image by using the grid representation, and then the convolutional neural network is directly used to identify the grid image for heart failure prediction. We evaluated the proposed methods in the monitoring data of real patients during the perioperative period.Results: In this paper, the results of our experiment demonstrate the Gradient Boosting Decision Tree (GBDT) classifier achieves the best results in the prediction of heart failure by statistical feature representation. The sensitivity, specificity and the area under the curve (AUC) of the best method can reach 83, 85 and 84% respectively.Conclusions: The experimental results demonstrate that representation learning model of vital signs monitoring data of intraoperative patients can effectively capture the physiological characteristics of postoperative heart failure. [ABSTRACT FROM AUTHOR]

Horizontal visibility (HVIS) is a primary index used for assessing air quality. Although satellite images provide information regarding atmospheric aerosols, atmospheric visibility is not directly measured. In this paper, a deep learning approach is proposed to retrieve HVIS using moderate-resolution imaging spectroradiometer (MODIS) aerosol optical depth (AOD) data, the European Centre for Medium-Range Weather Forecasts reanalysis dataset, and ground-based visibility observations. The deep neural network model comprises a multi-layer unsupervised restricted Boltzmann machine (RBM) and a layer for supervised learning. The dropout mechanism was used in the training process to overcome the errors caused by over-fitting. The results demonstrate that the correlation coefficient values between HVIS observations and retrievals during training, pre-validating, and evaluation were 0.74, 0.723, and 0.697, respectively. The retrieved HVIS in Eastern China exhibited a north-to-south increasing trend, increasing and decreasing in summer and winter, respectively. In conclusion, the proposed model presents an effective and more reliable method for HVIS retrieval. However, the small samples, low AOD, low albedo, high total column water, high longitude, and the low vertical wind component at 10 m likely cause HVIS bias. [ABSTRACT FROM AUTHOR]

Accurate, fast, and reliable estimation of field rock strength is significant for the assessment of rock mass strength. This paper presents a novel method to continuously estimate the field strength parameters of rock by incorporating a deep convolutional neural network (DCNN) technique into the drilling process. A DCNN model is established based on the stochastic pooling method and softmax loss. The proposed CNN model framework includes : (1) collecting drilling performance parameters of intact rock, (2) establishing a strength parameter database via standard laboratory tests , (3) training the proposed CNN model using images created from the dataset of drilling performance parameters and rock strength parameters (unconfined compressive strength (UCS), cohesion, and internal friction angle), and (4) performing a new estimation to evaluate the reliability of the trained CNN model. The experimental results show that the predicted rock strength parameters are within the accepted error range of 10% compared to the results from the conventional standard test. The proposed CNN shows superior performance for UCS estimation of various rock types and achieves higher accuracy than the Mohr–Coulomb criterion. In particular, the proposed method can overcome major limitations of analytical models based on the force limit and energy equilibrium method. This method enables continuous and reliable field measurements of rock strength parameters at a speed several orders of magnitude faster than the standard test. This continuous and practical technique has been applied in an engineering problem in the Hanjiang-to-Weihe River Project of China and shows potential for field applications in rock engineering. [ABSTRACT FROM AUTHOR]

Here we present our workflow and the final results of the 3D prospectivity modeling around the Zhuchong deposit undertaken during this study shown in terms of degree of connection values. The workflow is the core guiding ideology of our work. During the ore formation prediction, we tried to use weights of evidence method and artificial neural networks method to deal with the 3D cells data. And the results indicate these two methods can well predict the location of the known ore bodies. The reason may be that the copper deposits in Zhuchong Fe-Cu deposit are not concentrated but scattered, which makes making a certain influence to training samples in the neural network method. Which cause the defective result of neural network the result of neural network method is defective. What's more, the weight of evidence is also faster than the neural network method in speed. The results of the two prediction methods are roughly consistent. The similarity between these two prediction results indirectly reflects that two methods are feasible in Zhuchong Fe-Cu deposit. In the meanwhile, the prediction results are proved reliable and useful. The final prediction zone of metallogentic can be used as a target area for further exploration in Zhuchong mining area. • We use 3D ore formation prospectivity modeling and weights of evidence method and artificial neural networks method on the Zhuchong Fe-Cu deposit. • Result indicates that areas of known mineralization can be used to train 3D datasets to identify areas that are highly prospective for future exploration. • Compared the prediction results of the weight of evidence and the neural network, synthetically considering, for Zhuchong skarn Fe-Cu-Au deposit, the weight of evidence is more appropriate for the metallogenic prediction work. Our work has guiding significance for future deep prospecting and exploitation for other similar Fe-Cu skarn deposits. Three-dimensional (3D) metallogenic prospectivity modeling has become increasingly important in deep Fe-Cu skarn mineralization prospecting. The selection of prediction models and their comparison are of great significance. In this paper, we integrated the geological and geophysical data from the Zhuchong Fe-Cu deposit in the Yueshan orefield (Anhui, eastern China) to establish the local 3D geological framework. We extracted the 3D ore-controlling factors quantitatively by means of 3D spatial analysis methods, and compared the 3D mineralization locations predicted by the weight of evidence method and the artificial neural network method. The results show that both methods can locate most of the known orebodies, suggesting that both are relatively reliable. In addition, the weight of evidence method performed distinctly better than the artificial neural network method in terms of both prediction effectiveness and efficiency. Therefore, the weight of evidence method may be more applicable in 3D prospectivity modelling for Fe-Cu skarn deposits in the region. Finally, the composite area predicted by the two methods is taken as the final prediction result of the mineralization area of the deposit. And it is suggested that in the quantitative 3D prediction, multiple selection of different methods with good adaptability should be involved in the prediction at the same time, and compound prediction method should be used to delineate the target area. Our work has guiding significance for future deep prospecting and exploitation for other similar Fe-Cu skarn deposits. [ABSTRACT FROM AUTHOR]

Effective identification of lithology using well logs is one of the most important steps for reservoir characterization. A lot of methods have been developed to identify lithology automatically by analyzing the value or patterns of well logs. However, the response characteristics of log curves for some different lithologies are similar and indistinguishable. As a result, we may obtain results which do not follow the general geologic rules if we only use values or patterns of well logs as the criteria to identify lithology. In this paper, we propose an alternative automatic method to identify lithology by integrating both well logs and sedimentary patterns. First, we obtain the probability of lithology by applying the artificial neural networks (ANN) to the well logs. Then, we obtain the vertical combination patterns of different lithologies by applying a probabilistic statistical method to the cores. Finally, we produce an integrated lithology probability by combining the lithology probabilities calculated using ANN and lithology probabilities computed using sedimentary pattern. We validated our method by applying it to a real case study from China. The results indicate that the accuracy of lithology identification using the proposed method is much higher (91%) than that using neural networks method (83%). • Obtain the probability of each lithology from multiple well logs using ANN. • Convert the sedimentary patterns of lithologies observed in cores into the form of probability by a statistical method. • Integrate the two probabilities using a probability combination scheme, and predict lithology with the joint probability. [ABSTRACT FROM AUTHOR]

• Random forest model is applied to performance prediction of GSHP system. • The superiority of the method is verified from multiple angles. • Robustness, interpretability, and efficiency are taken into account. • This study enriches database of predictive model in energy management systems. With rapid development of artificial intelligence, data-driven prediction models play an important role in energy prediction, fault detection, and diagnosis. This paper proposes an ensemble approach using random forest (RF) for hourly performance predictions of GSHP system. Two years of in situ data were collected in an educational building situated in severe cold area in China. Prediction models were established for performance indicators, and results indicate that the average error for COP s , COP u , EER s and EER u were all controlled within 5%. The model established by small amount of data can accurately predict long-term performance, thereby reducing time and difficulty of data collection. RF models, trained with different parameter settings were compared, results indicate that model accuracy was not very sensitive to variables numbers. The impact of input variables on prediction performance was analyzed, and importance ranking changed with period and performance indicators. By comparing the variable importance list, it was possible to establish which parameters were abnormal and lists of different periods can reflect whether the energy structure of building has changed. The overall superiority of RF was verified by comparing with back propagation neural network (BPNN) from robustness, interpretability, and efficiency. First, since GSHP system involving multiple indicators, the robustness, measured by average accuracy, was used to evaluate the accuracy level. According to CV-RMSE, robustness of RF is approximately 3.3% higher than that of BPNN. Second, RF is highly interpretive but BPNN is typical black box model. Finally, modeling complexity and training time of BPNN were much greater than RF. [ABSTRACT FROM AUTHOR]

Quality management in shield tunneling projects is a challenging problem. To improve the quality of segment erection, the shield driver must constantly adjust the shield's attitude and position to reduce a snakelike motion for fitting the design tunnel axis based on the driver's experience, which is untimely and less reliable during excavation. Considering the disadvantage of this control method, this paper presents a predictive framework for the attitude and position in shield tunneling by applying a hybrid deep learning model. This framework contains a wavelet transform noise filter, convolutional neural network feature extractor, and long short-term memory predictor for determining the attitude and position of the shield machine in the future. The prediction framework is tested with the collected data of Mixshield operated in the river-crossing tunnel project of Yangtze Sanyang Road, Wuhan, China. Six variables characterizing the shield attitude and position are selected to validate the feasibility and performance of our method. Results reveal that the proposed model outperforms the other three similar models in predictive accuracy and provides decision support for adjusting the attitude and position in shield tunneling. • A new method for predicting the attitude and position of shield machine was proposed. • A hybrid deep learning model consisting of wavelet transform, CNN, and LSTM was constructed for the prediction task. • The on-site data collected from the largest river-crossing tunnel in China has been tested. • The prediction results comparing with other three models and the potential practice value were discussed. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence techniques such as artificial neural networks (ANN) and Support Vector Regression (SVM) have been well documented in ecological sciences. These methods can perfectly model complex and nonlinear structures, as well as with high processing power and quick computations in ecological sciences. Research on ecological issues with artificial intelligence methods can be useful and provided that the details of the use of these methods are necessary for readers. In this discussion, the discusser has tried to clarify the process of the paper of "Design of an integrated climatic assessment indicator (ICAI) for wheat production: A case study in Jiangsu Province, China" (doi: 10.1016/j.ecolind.2019.01.059). The discusser would like to call attention to some important points, which may be taken into consideration by the authors and other potential researchers. [ABSTRACT FROM AUTHOR]

Strawberry growers in Florida suffer from a lack of efficient and accurate yield forecasts for strawberries, which would allow them to allocate optimal labor and equipment, as well as other resources for harvesting, transportation, and marketing. Accurate estimation of the number of strawberry flowers and their distribution in a strawberry field is, therefore, imperative for predicting the coming strawberry yield. Usually, the number of flowers and their distribution are estimated manually, which is time-consuming, labor-intensive, and subjective. In this paper, we develop an automatic strawberry flower detection system for yield prediction with minimal labor and time costs. The system used a small unmanned aerial vehicle (UAV) (DJI Technology Co., Ltd., Shenzhen, China) equipped with an RGB (red, green, blue) camera to capture near-ground images of two varieties (Sensation and Radiance) at two different heights (2 m and 3 m) and built orthoimages of a 402 m2 strawberry field. The orthoimages were automatically processed using the Pix4D software and split into sequential pieces for deep learning detection. A faster region-based convolutional neural network (R-CNN), a state-of-the-art deep neural network model, was chosen for the detection and counting of the number of flowers, mature strawberries, and immature strawberries. The mean average precision (mAP) was 0.83 for all detected objects at 2 m heights and 0.72 for all detected objects at 3 m heights. We adopted this model to count strawberry flowers in November and December from 2 m aerial images and compared the results with a manual count. The average deep learning counting accuracy was 84.1% with average occlusion of 13.5%. Using this system could provide accurate counts of strawberry flowers, which can be used to forecast future yields and build distribution maps to help farmers observe the growth cycle of strawberry fields. [ABSTRACT FROM AUTHOR]

The Chinese tourism industry has been developing rapidly for the past several years, and the number of people traveling has been increasing year by year. However, many problems still beset current tourism management. Lack of effective management has caused numerous problems, such as tourists stranded during tourist season and the declining service quality of scenic spots, which have become the focus of tourists' attention. Network search data can intuitively reflect the attention of most users through the combination of the network search index and the back propagation (BP) neural network model. This study predicts the daily tourism demand in the Huangshan scenic spot in China. The filtered keyword in the Baidu index is added to the hybrid neural network, and a BP neural network model optimized by a fruit fly optimization algorithm (FOA) based on the web search data is established in this study. Different forecasting methods are compared in this paper; the results prove that compared with other prediction models, higher accuracy can be obtained when it comes to the peak season using the FOA-BP method that includes web search data, which is a sustainable means of practically solving the tourism management problem by a more accurate prediction of tourism demand of scenic spots. [ABSTRACT FROM AUTHOR]

Predicting the passenger flow of metro networks is of great importance for traffic management and public safety. However, such predictions are very challenging, as passenger flow is affected by complex spatial dependencies (nearby and distant) and temporal dependencies (recent and periodic). In this paper, we propose a novel deep-learning-based approach, named STGCNNmetro (spatiotemporal graph convolutional neural networks for metro), to collectively predict two types of passenger flow volumes—inflow and outflow—in each metro station of a city. Specifically, instead of representing metro stations by grids and employing conventional convolutional neural networks (CNNs) to capture spatiotemporal dependencies, STGCNNmetro transforms the city metro network to a graph and makes predictions using graph convolutional neural networks (GCNNs). First, we apply stereogram graph convolution operations to seamlessly capture the irregular spatiotemporal dependencies along the metro network. Second, a deep structure composed of GCNNs is constructed to capture the distant spatiotemporal dependencies at the citywide level. Finally, we integrate three temporal patterns (recent, daily, and weekly) and fuse the spatiotemporal dependencies captured from these patterns to form the final prediction values. The STGCNNmetro model is an end-to-end framework which can accept raw passenger flow-volume data, automatically capture the effective features of the citywide metro network, and output predictions. We test this model by predicting the short-term passenger flow volume in the citywide metro network of Shanghai, China. Experiments show that the STGCNNmetro model outperforms seven well-known baseline models (LSVR, PCA-kNN, NMF-kNN, Bayesian, MLR, M-CNN, and LSTM). We additionally explore the sensitivity of the model to its parameters and discuss the distribution of prediction errors. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for semantic segmentation of building roofs in dense urban environments with a Deep Convolution Neural Network (DCNN) using Chinese Very High Resolution (VHR) satellite (i.e., GF2) imagery. To provide an operational end-to-end approach for accurately mapping build roofs with feature extraction and image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform building roof segmentation. We selected typical cities with dense and diverse urban environments in different metropolitan regions of China as study areas, and sample images were collected over cities. High performance GPU-mounted workstations are employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with convolution layers is developed for building roof segmentation. The validation shows that the overall accuracy (OA) and the mean Intersection Over Union (mIOU) of DCNN-based semantic segmentation results are 94.67% and 0.85, respectively, and the CRF-refined segmentation results achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas in dense urban environments with different building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline of operational built-up area monitoring, and the timely update of building roof map could be applied in urban management and assessment of human settlement-related sustainable development goals over large areas. [ABSTRACT FROM AUTHOR]

Precipitation estimation with high-accuracy and spatiotemporal resolution is the key for distributed hydrological modelling. Gauge-satellite precipitation merging provides an effect way to improve the spatial precipitation estimation. In spite of the encouraging outcomes of gauge-satellite merging, it is quite a challenging job to derive precipitation appropriate for distributed watershed hydrological modeling when facing the following problems: (1) the spatial resolution of satellite-based precipitation product is much coarser than the modeled one; (2) the spatial distribution information of daily/sub-daily precipitation input to distributed hydrological models cannot be well captured by a single satellite-based precipitation product. In allusion to these problems, a two-step strategy for multi-source information merging was proposed in this paper to improve the spatial resolution and accuracy of daily precipitation estimates. The strategy is based on geographically weighted ridge regression kriging (GWRRK) with emphasis on dealing with non-stationarity and local collinearity in the regression context. Firstly, several individual satellite-based precipitation products, e.g., Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Aanlysis (TMPA) 3B42RT, Climate Prediction Center MORPHing technique (CMORPH), Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN), and Global Satellite Mapping of Precipitation (GSMaP), were downscaled to 1km by employing the relationships between precipitation and other environmental factors such as topography and vegetation. And then, all these downscaled products were merged with gauge observations. Considering the strongly skewed distribution of daily precipitation, Box-Cox transformation was carried out prior to the GWRRK approach to give a more normal distribution. To our knowledge, this is the first research to downscale satellite-based precipitation product at daily scale using geographically weighted regression method and to merge gauge observations and multiple satellite-based precipitation products. The two-step merging strategy was applied to an experiment conducted in Xijiang Basin of China from 2010 to 2017. Results showed that: (1) the regression relationships in spatial downscaling and gauge-multisatellites merging were strongly spatially non-stationary; (2) local collinearity existed in both steps: this problem was not serious in spatial downscaling but serious enough to be the main barrier for the application of geographically weighted (GWR) in gauge-multisatellites merging; (3) the spatial trend of the downscaled data was consistent with that of the original data for all the four satellite-based daily precipitation products; (4) the merging of gauge observations and multiple satellite-based precipitation products provided more accurate estimates than the merging of gauge observations and a single satellite-based precipitation product. The GWRRK-based two-step merging strategy presented in this study has provided an efficient way to derive daily precipitation with high-accuracy and spatiotemporal resolution. [ABSTRACT FROM AUTHOR]

Abstract: Water quality monitoring and forecasting plays an important role in modern intensive fish farming management. This paper describes an online water quality monitoring system for intensive fish culture in China, which combined web-server-embedded technology with mobile telecommunication technology. Based on historical data, this system is designed to forecast water quality with artificial neural networks (ANNs) and control the water quality in time to reduce catastrophic losses. The forecasting model for dissolved oxygen half an hour ahead has been validated with experimental data. The results demonstrate that multi-parametric, long-distance and online monitoring for water quality information can be accurately acquired and predicted by using this established monitoring system. [Copyright &y& Elsevier]

Economic practitioners in China are giving up the classical Leontief's Input-Output analysis methods. This paper offers an alternative method of input-output analysis. The proposed method is based on the layered neural network model. It shows that neural networks method can be useful for input-output analysis for a dynamic economic system. [ABSTRACT FROM AUTHOR]