Combinations Of Input Features Research Articles

Quantitative detection of moisture content of corn by olfactory visualization technology

In this study, a novel method for quantitatively detecting the moisture content of corn by olfactory visualization technology is proposed. First of all, an olfactory visualization system was developed to obtain odor information of corn samples with varying moisture contents using sensor arrays. The sensor array was constructed with twelve chemical dyes, which helped assemble the system. Then, the RreliefF algorithm was utilized to sort the characteristic variables of the sensor image by weight, and the analytical model based on different combinations of input features was built using support vector regression (SVR). Moreover, the ability of three optimization algorithms, namely grid search (GS), particle swarm optimization (PSO) and dung beetle optimizer (DBO), was compared to determine their effectiveness in optimizing the parameters of the SVR model. The results reveal that the RreliefF-GS-SVR model demonstrates an enhanced correlation coefficient of prediction (RP), with an increase from 0.97 to 0.98, as well as the root mean square error of prediction (RMSEP), is reduced from 0.66% to 0.53% when compared to the GS-SVR model. Similarly, in comparison to the RreliefF-GS-SVR model and RreliefF-PSO-SVR model, the RreliefF-DBO-SVR model shows better predictive performance, with an increase in RP to 0.99 and a decrease in RMSEP to 0.25%. The comprehensive findings indicate that integrating olfactory visualization technology and multivariate analysis is feasible for conducting quantitative analysis of grain moisture content.

Extraction of eutrophic and green ponds from segmentation of high-resolution imagery based on the EAF-Unet algorithm

Inland ponds exhibit remarkable ubiquity across the globe, playing a vital role in the sustainability of global continental freshwater resources and contributing significantly to their biodiversity. Numerous ponds are eutrophic and experience recurrent seasonal or year-round algal blooms or persistent duckweed cover, conferring a characteristic green hue. Here, we denote these eutrophic and green ponds as EGPs. The excessive proliferation of algal blooms and duckweed within these EGPs poses a significant threat to the ecological functioning of these aquatic systems, which can lead to hypoxia or the release of microcystins. To identify these EGPs automatically, we constructed an Efficient Attention Fusion Unet (EAF-Unet) algorithm using Gaofen-2 (GF2) panchromatic and multispectral imagery. The attention mechanism was incorporated in Unet to help better detect EGPs. Using the first EGP labeled dataset, we determined the best input feature combination (RGB, NIR, NDVI, and Bright) and the most effective encoding (Rasnet50) for EAF-Unet for distinguishing EGPs from other ground cover types. The evaluation indices – Precision (0.81), Recall (0.79), F1-Score (0.80), and Intersection over Union (IoU, 0.67) – indicate that EAF-Unet can accurately and robustly extract EGPs from GF2 images without relying on pond water masks. Remote-sensing EGP products can assist in identifying ponds with severe eutrophication. Moreover, these products can serve as references for identifying high-risk areas prone to improper sewage discharge or inadequate sewer construction.

Neural network energy management strategy with optimal input features for plug-in hybrid electric vehicles

The neural network energy management strategy can be implemented online and effectively save the energy for the plug-in hybrid electric vehicles (PHEVs). However, the selection of input features and application to untrained driving cycles are two issues faced by the strategy. This paper proposes an energy management strategy with the optimal input features for the PHEV. The global optimal datasets are first obtained based on the dynamic programming (DP) algorithm. Then the random forest classification models are trained with different combinations of input features to select the input feature combination with the highest classification accuracy. A neural network with the selected input features is finally trained using the optimal datasets for online control. With the optimal input features, the strategy can be adopted to both trained driving cycles and untrained driving cycles. Results demonstrate that the proposed strategy can save 4.44% to 7.75% energy compared to the charge depleting and charge sustaining strategy on trained cycles and 3.80% to 7.70% on untrained cycles respectively. The efficiency of the proposed strategy is only less than 2.41% worse than the DP algorithm.

Lidar-based virtual load sensors for mooring lines using artificial neural networks

Floating offshore wind turbines are equipped with a variety of sensors, which are measuring data, valuable for the control and monitoring of the turbine. However, reliable measurements are difficult or costly for some physical quantities. This includes load estimates for mooring lines and fairleads. In this study, we investigate an approach using wind speed measurements from a forward-looking nacelle-based lidar as inputs to long short-term memory networks to estimate fairlead tensions. Nacelle-based lidar wind speed measurements on floating offshore wind turbines are influenced by platform motions, in particular by the rotational pitch displacement and the surge displacement of the floater. Therefore, the lidar wind speed measurement contains information about the dynamic behavior of the floater. In turn, the floater’s dynamics determine the fair lead loads. Thus in this study, we directly use the lidar-measured line of sight (LOS) wind speeds to estimate mooring line tensions. The model training data is obtained using the aero-elastic wind turbine simulation tool openFAST in combination with the numerical lidar simulation framework ViConDAR. Results show, that lidar-based virtual load sensors can reproduce mean fairlead tension as well as low-frequency fluctuations, with varying accuracy dependant on the combination of input features. For the model which is only using LOS wind speed measurements as input a normalized root mean squared error of 0.55 was obtained.

Deep-learning-enhanced digital twinning of complex composite structures and real-time mechanical interaction

Digital twins are undergoing growth that enables highly informative and scaleable interaction between physical objects and virtual twins, which is of great significance to the life cycle analysis of composites. Real-time fine evolution is challenging due to vast combinations of input features and high-resolution calculated variables. Here, we systematically demonstrate an AI-based methodology for digital twinning of complex composite structures. First, three types of deep neural networks are created with optionally used autoencoders as surrogate models, with architectures and data processing inspired by the rule-of-mixture of composites. Second, the prediction accuracy and efficiency are evaluated quantitatively and qualitatively, demonstrating the feasibility of predicting 3D displacement and stress fields directly from sensing data of temperature, pressure and loading displacement, and the optimal architecture is selected to be the evolving digital twin. Finally, the real-time interactive experiments are relayed to the digital twin and demonstrated that it can interact with physical objects and evolve online with high accuracy. These results indicate that the computational time can be reduced by 3∼6 orders of magnitude with high information intensity and scalability compared with conventional numerical and experimental methods, which opens up the avenues for the cost-effective and efficient development of digital twin services for composites.

Nonlinear input feature reduction for data-based physical modeling

This work introduces a novel methodology to derive physical scalings for input features from data. The approach developed in this article relies on the maximization of mutual information to derive optimal nonlinear combinations of input features. These combinations are both adapted to physics-related models and interpretable (in a symbolic way). The algorithm is presented in detail, then tested on a synthetic toy model. The results show that our approach can effectively construct relevant combinations by analyzing a strongly noisy nonlinear dataset. These results are promising and may significantly help training data-driven models. Finally, the last part of the paper introduces a way to account for the physical dimension of data. The test case is a synthetic dataset inspired by the Law of the Wall from turbulent boundary layer theory. Once again, the algorithm shows that it can recover relevant nondimensional variables for data-base modeling.

Using NDVI, climate data and machine learning to estimate yield in the Douro wine region

Estimating vineyard yield in advance is essential for planning and regulatory purposes at the regional level, with growing importance in a long-term scenario of perceived climate change. With few tools available, the current study aimed to develop a yield estimation model based on remote sensing and climate data with a machine-learning approach. Using a satellite-based time-series of Normalized Difference Vegetation Index (NDVI) calculated from Sentinel 2 images and climate data acquired by local automatic weather stations, a system for yield prediction based on a Long Short-Term Memory (LSTM) neural network was implemented. The study was conducted in the Douro Demarcated Region in Portugal over the period 2016–2021 using yield data from 169 administrative areas that cover 250,000 ha, in which 43,000 ha of the vineyard are in production. The optimal combination of input features, with an Mean Absolute Error (MAE) of 672.55 kg/ha and an Mean Squared Error (MSE) of 81.30 kg/ha, included the NDVI, Temperature, Relative Humidity, Precipitation, and Wind Intensity. The model was tested for each year, using it as the test set, while all other years were used as input to train the model. Two different moments in time, corresponding to FLO (flowering) and VER (veraison), were considered to estimate in advance wine grape yield. The best prediction was made for 2020 at VER, with the model overestimating the yield per hectare by 8 %, with the average absolute error for the entire period being 17 %. The results show that with this approach, it is possible to estimate wine grape yield accurately in advance at different scales.

Prediction of significant wave height in hurricane area of the Atlantic Ocean using the Bi-LSTM with attention model

The Bi-LSTM with attention (BLA) model is proposed to predict wave height in the hurricane area of the Atlantic Ocean. Four data features (wave height, wind speed, wind direction, and wave direction) collected at five buoy stations are selected as model inputs, while future wave height is specified as model output. Predictions are obtained for 1-h, 3-h, 6-h, and 12-h lead times. Two evaluation metrics are introduced to evaluate the accuracy and stability of the model. Influencing factors such as input–output ratio and input feature combination are studied. For the input–output ratio, it is found that the shorter lead time requires a larger ratio, with a ratio of 9:1 required for 1-h lead time prediction, with 3:1 for 3-h prediction, 2:1 for 6-h prediction, and 1:1 for 12-h prediction. For the input feature combination, the combination of the wave height, the wind speed, and the coupling of the wind direction and wave direction via the cosine function holds the best prediction performance in 1-h and 3-h lead time prediction. And for 6-h and 12-h forecasts, a combination of wave height and wind speed is best. By comparing overall evaluation metrics and extreme wave height prediction results of the BLA model with those of the Bi-LSTM, LSTM, and LSTM with attention models, we notice that the BLA model has the best and most stable prediction performance.

What Does Your Bio Say? Inferring Twitter Users’ Depression Status From Multimodal Profile Information Using Deep Learning

People suffering from stress and various mental health problems find it easier to express and share their feelings on online platforms, such as Twitter. However, the imposed character limit (280 characters) by Twitter and infrequent online activities of a section of users poses a serious setback in using computational methods for mental health analysis or emotion research. Twitter provides rich metadata information about its users (such as user’s description, geolocation, and profile image URL), which can provide valuable information regarding the mental state of the users. We hypothesize that Twitter’s rich metadata information about their users can provide some valuable depression cues, which may help in an early low-profile evaluation. In this article, we investigate this hypothesis by developing an end-to-end multimodal multitask (MT) system for depression detection (primary task) and emotion recognition (auxiliary task), where the variation of emotion information based on different user descriptions assists the learning of the primary task. The proposed system attains 70% accuracy on the depression detection task outperforming several single-task (ST) baselines built on the various combination of input features. Our findings indicate that Twitters’s rich metadata information can be leveraged to detect depression among users with significant confidence.

Design optimization of a multi-layer porous wave absorber using an artificial neural network model

The design optimization of a multi-layer porous wave absorber has been achieved through the supervised artificial neural network (ANN) and analytical model validated by CFD and experiments. The analytical model is established by means of a matched eigenfunction expansion method (MEEM) by applying the boundary condition with a quadratic relationship between the pressure drop and traversing fluid velocity at the porous plates. Along with the reflection coefficient as a target feature, input key features of the multi-layer porous wave absorber are selected through the parametric study. A dataset with 200 combinations of input design features is generated by the developed analytical model. Using the dataset, the ANN model is trained with a R2 score of 0.97. Predictions are generated for a large sample set with the trained ANN model. Top 1% combinations of input features that yield a minimum value of the reflection coefficient are used for the optimal design of the wave absorber. Based on the interquartile range (IQR) value of this 1% data, it is found that the most important design features are the porosity and submergence depth of the upmost plate and their optimal ranges for a double-layer wave absorber are 0.055≤d1/h≤0.067 and 0.117≤P1≤0.173. The optimal range of design features can be used as a guideline for the design of an effective wave absorber.

Prediction of growth in grower-finisher pigs using recurrent neural networks

Accurate prediction of pig growth is an important tool for supporting sustainable global pork production, due to the potential benefits to farm management in monitoring growth according to target, promoting efficient use of resources and planning sale of finished animals. In this paper, a long short-term memory (LSTM) recurrent neural network architecture was designed to predict how long it would take for grower-finisher pigs housed in a climate-controlled building reflecting commercial practice to reach a target liveweight of 90 kg. To make these predictions, data on pig liveweight and food consumption were integrated, along with various combinations of environmental temperature recorded by the building control system and, to represent seasonality, encodings of day of the year. Also, ensembles were created and evaluated by averaging the predictions of multiple models, each trained with different combinations of input features, and comparisons were made between the performance of the LSTM models and other machine learning algorithms. Overall, the LSTM model achieved the best prediction performance, with a RMSE of 2.470 days and a Pearson's correlation coefficient of 0.962. Integrating both environmental temperature and seasonality data into the models generally resulted in an improvement in predictive performance. The results demonstrate the potential of LSTM models as a precision livestock farming tool for the early prediction of growth in commercial finisher pigs. • A machine learning pipeline for the forecasting of pig growth was designed. • Predicting the time to reach a target weight can improve data availability. • Specialised neural network architectures are very effective at predicting growth. • Utilising environmental temperatures can improve growth prediction accuracy. • Specialised algorithms can be used to remove outliers from non-cyclical time series.

RECHOmmend: An ECG-Based Machine Learning Approach for Identifying Patients at Increased Risk of Undiagnosed Structural Heart Disease Detectable by Echocardiography.

Background:Timely diagnosis of structural heart disease improves patient outcomes, yet many remain underdiagnosed. While population screening with echocardiography is impractical, ECG-based prediction models can help target high-risk patients. We developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography.Methods:Using 2 232 130 ECGs linked to electronic health records and echocardiography reports from 484 765 adults between 1984 to 2021, we trained machine learning models to predict the presence or absence of any of 7 echocardiography-confirmed diseases within 1 year. This composite label included the following: moderate or severe valvular disease (aortic/mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction <50%, or interventricular septal thickness >15 mm. We tested various combinations of input features (demographics, laboratory values, structured ECG data, ECG traces) and evaluated model performance using 5-fold cross-validation, multisite validation trained on 1 site and tested on 10 independent sites, and simulated retrospective deployment trained on pre-2010 data and deployed in 2010.Results:Our composite rECHOmmend model used age, sex, and ECG traces and had a 0.91 area under the receiver operating characteristic curve and a 42% positive predictive value at 90% sensitivity, with a composite label prevalence of 17.9%. Individual disease models had area under the receiver operating characteristic curves from 0.86 to 0.93 and lower positive predictive values from 1% to 31%. Area under the receiver operating characteristic curves for models using different input features ranged from 0.80 to 0.93, increasing with additional features. Multisite validation showed similar results to cross-validation, with an aggregate area under the receiver operating characteristic curve of 0.91 across our independent test set of 10 clinical sites after training on a separate site. Our simulated retrospective deployment showed that for ECGs acquired in patients without preexisting structural heart disease in the year 2010, 11% were classified as high risk and 41% (4.5% of total patients) developed true echocardiography-confirmed disease within 1 year.Conclusions:An ECG-based machine learning model using a composite end point can identify a high-risk population for having undiagnosed, clinically significant structural heart disease while outperforming single-disease models and improving practical utility with higher positive predictive values. This approach can facilitate targeted screening with echocardiography to improve underdiagnosis of structural heart disease.

COVID-19 Epidemic Analysis in India with Multi-Source State-Level Datasets.

The COVID-19 pandemic has been a global crisis affecting billions of people and causing countless economic losses. Different approaches have been proposed for combating this crisis, including both medical measures and technical innovations, e.g., artificial intelligence technologies to diagnose and predict COVID-19 cases. While there is much attention being paid to the USA and China, little research attention has been drawn to less developed countries, e.g., India. In this study, I conduct an analysis of the COVID-19 epidemic in India, with datasets collected from different sources. Several machine learning models have been built to predict the COVID-19 spread, with different combinations of input features, in which the Transformer is proven as the most precise one. I also find that the Facebook mobility dataset is the most useful for predicting the number of confirmed cases. However, I find that the datasets from different sources are not very effective when predicting the number of deaths caused by the COVID-19 infection.

An adaptive feature selection schema using improved technical indicators for predicting stock price movements

Accurate stock market forecasts can bring high returns for investors. There have been a growing number of studies employing machine learning technology to perform stock prediction tasks with the development of machine learning and artificial intelligence technologies. However, accurately predicting stock price trends still is an elusive goal, not only because the stock market is affected by policies, market environment, market sentiment, etc., but also because stock price data is inherently complex, noisy, and nonlinear. Many technical indicators have been used as input features to stock prediction models, but the quality of technical indicators has always been a neglected issue, thus the application of feature engineering in stock prediction tasks needs to be further expanded. Using 18 technical indicators as the original features, this paper presents improved technical indicators based on wavelet denoising and a novel two-stage adaptive feature selection method. Finally, the random forest model is used as the stock prediction model. Experiments show that in contrast to the original technical indicators, the improved technical indicators significantly enhance the performance of the model (e.g., F1 scores increased by 34.48% on the SSE Composite Index (SSEC) data set, 41.56% on the Hang Seng Index (HSI) data set, 34.48% on the Dow Jones Industrial Average (DJI) data set, 32.75% on the Standard & Poor's 500 Index (S&P 500) data set). The experimental results verify the importance of the quality of technical indicators in the task of stock prediction. Meanwhile, the results also demonstrate the effectiveness of the feature selection method, which can achieve higher prediction accuracy with fewer features. In addition, we established multiple data sets according to the size-varied time windows to study the influence of the size-varied time windows. The results show that properly increasing the size of the time window can exert a positive impact on the model. Finally, by utilizing our two-stage adaptive feature selection method, we remove redundant features, and achieve excellent results on data sets from four different stock markets (e.g., F1 scores reached 0.754 on the SSEC data set, 0.794 on the HSI data set, 0.789 on the DJI data set, 0.821 on the S&P 500 data set). Overall, this study experimentally verifies that improving feature quality can positively impact model performance, and that choosing an appropriate combination of input features can not only improve model performance, but reduces the negative impact of the curse of dimensionality as well.

A machine learning-based method for prediction of ship performance in ice: Part I. ice resistance

This article focuses on design of an Artificial Neural Network (ANN) model to estimate ship resistance in ice-covered water by using suitable ship and ice parameters. In order to develop a reliable model, as much ice resistance test data as from the ship sea trials and model test measurements are collected to train the neural network. Different features (ship design parameters and ice mechanic properties) are explored to find a suitable combination of input features. Several algorithms are tested and compared to select a good model for resistance prediction. It turns out that seven features and the Radial Basis Function - Particle Swarm Optimization algorithm (RBF-PSO) can provide a reasonable generalization model. This study shows that the ice resistance predicted by the ANN correlates well with the measured data. The model developed herein can be used as an ice resistance prediction tool with high accuracy compared to the conventional semi-empirical formulae used in polar ship design.

Diagnosis for multiple faults of chiller using ELM-KNN model enhanced by multi-label learning and specific feature combinations

Existing fault detection and diagnosis methods for chillers are usually very effective on single faults diagnosis, but perform poorly while diagnosing multiple faults, and these fault diagnosis models depend on the range of training data. Such models tend to fail when the system encounters a fault that was not included in training data. This paper presents a novel multiple faults diagnosis method for chiller based on multi-label learning and specific feature combinations enhanced ELM-KNN. Firstly, Extreme Learning Machine (ELM) is used for mapping of features to improve the accuracy of K-Nearest Neighbor (KNN) algorithm for multiple faults. Then, through multi-label learning, a model is established for each single fault, and by merging these models a final multiple faults diagnosis model is formed. Finally, by examining the input features, the specific combinations of input features for each single fault are determined and applied to the actual chiller. Experimental results show that the model proposed in this paper has the highest accuracy among the compared methods. The model proposed has achieved better diagnosis performance for the multiple faults in the absence of several multiple faults training data. The specific feature combinations are beneficial to improve the diagnosis performance of the model. The model can have excellent diagnostic performance for both normal operation and multiple faults by only using a small amount of single fault data in training. In addition, the model proposed can also complete the diagnosis of single faults in the absence of some single faults training data.

Separability of Input Features and the Resulting Accuracy in Classifying Target Poses for Active Transhumeral Prosthetic Interfaces.

In active prostheses, it is desired to achieve target poses for a given family of tasks, for example, in the task of forward reaching using a transhumeral prosthesis with coordinated joint movements. To do so, it is necessary to distinguish these target poses accurately using the input features (e.g. kinematic and sEMG) obtained from the human users. However, the input features have conventionally been selected through human observations and influenced heavily by the availability of sensors in this context, which may not always yield the most relevant information to differentiate the target poses in the given task. In order to better select from a pool of available input features, those most appropriate for a given set of target poses, a measure that correlates well with the resulting classification accuracy is required so that it can inform the interface design process. In this paper, a scatter-matrix based class separability measure is adopted to quantitatively evaluate the separability of the target poses from their corresponding input features. A human experiment was performed on ten able-bodied subjects. Subjects were asked to perform forward-reaching movements with their arms on nine target poses in a virtual reality (VR) platform and the corresponding kinematic information of their arm movement and muscle activities were recorded. The accuracy of the prosthetic interface in determining the intended target poses of the human user during forward reaching is evaluated for different combinations of input features, selected from the kinematic and sEMG sensors worn by the users. The results demonstrate that employing input features that yield a high separability measure between target poses results in a high accuracy in identifying the intended target poses in the execution of the task.

Mowing event detection in permanent grasslands: Systematic evaluation of input features from Sentinel-1, Sentinel-2, and Landsat 8 time series

The intensity of land use and management in permanent grasslands affects both biodiversity and important ecosystem services. Comprehensive knowledge about these intensities is a crucial factor for sustainable decision-making in landscape policy. For meadows, the management intensity can be described by proxies such as the mowing frequency, usually, a higher number of cuts indicate higher intensities. Dense time series of medium resolution (10–30 m) remote sensing data are suitable for the detection of mowing events. However, existing studies revealed a general lack of consensus about the most appropriate input data set for a consistent and reliable mowing detection.We systematically evaluated the synergistic use of acquisitions from Sentinel-1, Sentinel-2, and Landsat 8 to detect the occurrence, frequency, and date of mowing events as an indicator of grassland management intensity. Dense time series of NDVI (Sentinel-2 and Landsat 8), γ0 backscatter, backscatter cross-ratio, backscatter second-order texture metrics as well as 6-day interferometric coherence (Sentinel-1) were used as input features. All possible combinations of input features were tested to train a one-dimensional convolutional neural network, which enables enhanced exploitation of the temporal domain of the data. The evaluation was conducted on 64 meadows for an overall of 257 mowing events from 2017 to 2019 in Germany.Our results revealed that the combination of input features improves the detection performance. The highest overall accuracy was reached by a combination of NDVI, backscatter cross-ratio, and interferometric coherence with an F1-Score of 0.84. The mowing frequency was predicted with a mean absolute error of 0.38 events per year, while the date of the events was missed by 3.79 days on average. NDVI time series alone mostly underperformed in comparison to optical/SAR combinations but clearly outperformed input-sets that were solely based on SAR features. The proposed model performed well for meadows with low to medium management intensities but further testing is recommended for highly intensive managed parcels.The results clearly demonstrate the additional value of fusing time series of the three present Earth observation systems that deliver a freely available global coverage of the land surface at medium resolution.

Predicting traffic demand during hurricane evacuation using Real-time data from transportation systems and social media

In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of people across multiple states in the United States. Under hurricane evacuation, efficient traffic operations can maximize the use of transportation infrastructure, reducing evacuation time and stress due to massive congestion. Evacuation traffic prediction is critical to plan for effective traffic management strategies. However, due to the complex and dynamic nature of evacuation participation, predicting evacuation traffic demand long ahead of the actual evacuation is a very challenging task. Real-time information from various sources can significantly help us reliably predict evacuation demand. In this study, we use traffic sensor and Twitter data during hurricanes Matthew and Irma to predict traffic demand during evacuation for a longer forecasting horizon (greater than 1 h). We present a machine learning approach using Long-Short Term Memory Neural Networks (LSTM-NN), trained over real-world traffic data during hurricane evacuation (hurricanes Irma and Matthew) using different combinations of input features and forecast horizons. We compare our prediction results against a baseline prediction and existing machine learning models. Results show that the proposed model can predict traffic demand during evacuation well up to 24 h ahead. The proposed LSTM-NN model can significantly benefit future evacuation traffic management.

Short-Term Wind Power Forecasting Using Mixed Input Feature-Based Cascade-connected Artificial Neural Networks

Accurate short-term wind power forecasting is crucial for the efficient operation of power systems with high wind power penetration. Many forecasting approaches have been developed in the past to forecast short-term wind power. Artificial neural network-based approaches (ANNs) have become one of the most effective and popular short-term wind speed and wind power forecasting approaches in recent years. However, most researchers have used only historical data from a specific station to train the ANNs without considering meteorological variables from many neighboring stations on the forecasting performance. Using additional meteorological variables from neighboring stations can contribute valuable surrounding information to the forecasting model of the target station and improve ANNs performance. In this paper, a mixed input features-based cascade-connected artificial neural network (MIF-CANN) is used to train input features from many neighboring stations without encountering overfitting issues caused by many input features. Multiple ANNs train different combinations of input features in the first layer of the MIF-CANN model to produce preliminary results, then cascading into the second phase of the MIF-CANN model as inputs. The performance of the proposed MIF-CANN model is compared with the ANNs-based spatial correlation models. Simulation results show that the proposed MIF-CANN has better performance than the ANNs-based spatial correlation models.