Search

Accurate and reliable prediction of PM2.5 concentrations is the basis for appropriate warning measures, and a single prediction model is often ineffective. In this paper, we propose a novel decomposition-and-ensemble model to predict the concentration of PM2.5. The model utilizes Ensemble Empirical Mode Decomposition (EEMD) to decompose PM2.5 series, Support Vector Regression (SVR) to predict each Intrinsic Mode Function (IMF), and a hybrid algorithm based on Differential Evolution (DE) and Grey Wolf Optimizer (GWO) to optimize SVR parameters. The proposed prediction model EEMD-SVR-DEGWO is employed to forecast the concentration of PM2.5 in Guangzhou, Wuhan, and Chongqing of China. Compared with six prediction models, the proposed EEMD-SVR-DEGWO is a reliable predictor and has achieved competitive results. [ABSTRACT FROM AUTHOR]

Urban land change plays an essential role in the development of country's economy. Rapid and unplanned urban growth increases land surface temperature (LST) and reduces carbon storage (CS) by replacing the natural land use/land cover (LULC). This paper aims to monitor and predict the changes in urban growth patterns on LST and CS for the winter season in Guangzhou from 1989 to 2021. The integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model is used to assess the existing (1989-2021) scenario of CS. The Cellular Automata-Artificial Neural Network (CA-ANN) and Long Short Term Memory (LSTM) based Whale Optimization Algorithm (WOA) are used to predict the future LULC, CS and LST scenarios. The results indicate that an increase in urban areas by 63% causes an upsurge of high LST (≥34 °C) areas by 652 km2 and a decrease in carbon storage by 56,943.607 t from 1989 to 2021. In addition, the results demonstrate that 93% of lower temperature areas have higher CS capacity (65%), whereas 80% of higher temperature areas demonstrate a low CS capacity (89%). This study can provide effective mitigating measures for designing smart cities and valuable guidelines for ensuring environmental-friendly green cities. [ABSTRACT FROM AUTHOR]

Accurate short-term traffic state prediction is a crucial requisite for control and guidance of traffic flow in the intelligent traffic system, which has attracted increasing attention in the transportation field recently. This paper tests the optimization performances of two emerging bionic algorithms, known as Cuckoo Search Algorithm (CS) and Bat Algorithm (BA). Combined with the Support Vector Regression (SVR) principle, the two aforementioned algorithms are applied to optimize the kernel function parameters in SVR. At last, the speed data of a road network in Guangzhou are collected. The prediction performances of the CS-SVR and BA-SVR models are tested after preprocessing the data. From the overall prediction rates, the CS-SVR algorithm is slightly better than BA-SVR in terms of calculating speed. Furthermore, the two algorithms are significantly superior to the traditional SVR model and long short-term memory networks (LSTM), thereby verifying their effectiveness and practicability in short-term traffic state prediction. [ABSTRACT FROM AUTHOR]

With rapid economic growth since the 21st century, cities in China have experienced considerable economic and social reconstruction. Driven by rapid industrialization, urban spatial structures are undergoing evolution and change. Therefore, this paper analyzes the processes and mechanisms associated with the evolution of the commercial spatial structure in Guangzhou after the financial crisis in 2008 based on both theoretical and empirical analyses. We use a Dirichlet multinomial regression (DMR) model to extract latent semantic information and determine urban functional areas from global positioning system (GPS) and point-of-interest (POI) data collected in Guangzhou in 2009 and 2013. In addition, we use movement patterns and POI data to identify the evolution of Guangzhou's commercial zones from 2009 to 2013. The results show that the urban commercial structure in Guangzhou gradually changed from a single-center model to a multi-center model with dispersed clusters and that the distribution of the entire spatial structure changed. Meanwhile, Guangzhou’s commercial structure not only varied over time but also exhibited specific geographical features. This paper demonstrates that the proposed method can clearly identify the boundary of the commercial area in Guangzhou and provides a valid spatial-temporal model of change in the city. Moreover, this study not only expounds the future development trends of the urban spatial structure in Guangzhou from a microcosmic perspective but also provides a scientific basis for clarifying the spatial locations and development advantages of urban functions within the city. [ABSTRACT FROM AUTHOR]

Summary: A higher accurate load forecasts can significantly reduce the potential cost for power system operation and power market decision. There have been extensive load forecasting methods proposed by now. Ensemble learning is an effective way to integrate various forecasts and further improve the forecasting accuracy. Traditional ensemble learning algorithms static. However, how to select a suitable forecasting method from a large number of load forecasting methods under the complex and varying environment conditions is still challenging. In this context, this paper proposes a dynamic integration approach for multiple load forecasts based on reinforcement learning. Compared with the traditional integration methods, this method adopts Q‐learning algorithm to realize the adaptive selection of the forecasting methods and dynamic weight calculation for different and varying environment. The basic principles and implementation processes of Q‐learning algorithm is firstly introduced. Then, the implementation methodology of dynamic integration approach of multiple load forecasts is proposed. On this basis, the environment state, action space and return function are designed according to the requirements of Q‐learning algorithm. Finally, a case study based on the real‐world data in Guangzhou shows that the average forecasting accuracy could be improved by almost 3% by adopting the dynamic integration approach with the traditional ones. [ABSTRACT FROM AUTHOR]

Complex nonlinear optimization problems are involved in optimal spatial search, such as location allocation problems that occur in multidimensional geographic space. Such search problems are generally difficult to solve by using traditional methods. The bat algorithm (BA) is an effective method for solving optimization problems. However, the solution of the standard BA is easily trapped at one of its local optimum values. The main cause of premature convergence is the loss of diversity in the population. The niche technique is an effective method to maintain the population diversity, to enhance the exploration of the new search domains, and to avoid premature convergence. In this paper, a geographic information system- (GIS-) based niche hybrid bat algorithm (NHBA) is proposed for solving the optimal spatial search. The NHBA is able to avoid the premature convergence and obtain the global optimal values. The GIS technique provides robust support for processing a substantial amount of geographical data. A case in Fangcun District, Guangzhou City, China, is used to test the NHBA. The comparative experiments illustrate that the BA, GA, FA, PSO, and NHBA algorithms outperform the brute-force algorithm in terms of computational efficiency, and the optimal solutions are more easily obtained with NHBA than with BA, GA, FA, and PSO. Moreover, the precision of NHBA is higher and the convergence of NHBA is faster than those of the other algorithms under the same conditions. [ABSTRACT FROM AUTHOR]

With the boom of big data, the Internet contains more and more personal behavior information, but it is difficult to extract effectively. A model involving multivariate processing capability must be constructed to deal with these time series with complex characteristics. In this paper, a novel hybrid model embedding Baidu Search Index is therefore proposed to implement multi-step ahead subway passenger flow forecasting. Firstly, we collect data from informative Baidu Search Index, reduce dimensionality, and screen out the powerful predictors by statistical analysis. Secondly, we extract matching common modes at similar time scales between the subway passenger flow and screened Baidu Search Index via multivariate mode decomposition being optimized by multi-objective algorithm. Furthermore, to eliminate pseudo statistical causality, we select the optimal combination of modal components between subway passenger flow and its corresponding Baidu Search Index at each time scale by an innovative multi–modal analysis strategy. Thirdly, we reconstruct the forecasting values of each selected optimal combination as the final results. The empirical results of Beijing, Shanghai and Guangzhou show that the proposed model can significantly outperform six benchmark models in both the level and directional accuracy. So introducing Baidu Search Index creates a sound opportunity to enhance the subway passenger flow forecasting ability. [ABSTRACT FROM AUTHOR]

• A novel two-stage robust optimization model is developed for the line planning with passenger demand uncertainty. • A Lagrange relaxation-based heuristic as well as some strengthening techniques is introduced to solve the robust model. • The model and algorithm are tested for case studies of a Chinese high-speed railway line. A railway line-planning problem is one of the fundamental problems in the strategic planning of railway operations. Operation zone, frequency, stop schedule, and passenger distribution for each train based on passenger demand are determined to minimize both the operation cost of the railway enterprise and the total travel cost to the passengers. However, passenger demand uncertainty makes balancing transport capacity and fluctuating demand challenging. Therefore, this paper proposes a two-stage robust optimization model wherein the nominal line plan is determined in the first stage (i.e., the case in which passenger demand has no fluctuation) and the rescheduled line plan based on the nominal line plan is determined according to the demand realization in the second stage. A Lagrangian relaxation algorithm and some strengthening techniques are designed. The model and algorithm are tested on real-world instances of the Wuhan–Guangzhou high-speed railway line under uncertain passenger demands. Computational results indicate that the proposed solution algorithm can yield a high-quality solution in 3600 s. In addition, the proposed two-stage robust solution can help minimize both operation and travel costs on average when compared with the nominal solution under uncertainty realization. [ABSTRACT FROM AUTHOR]