Comparative analysis of kernel-based versus  ANN and deep learning methods in  monthly reference evapotranspiration estimation

Abstract. Timely and accurate estimation of reference evapotranspiration (ET0) is indispensable for agricultural water management for efficient water use. This study aims to estimate the amount of ET0 with machine learning approaches by using minimum meteorological parameters in the Corum region, which has an arid and semi-arid climate and is regarded as an important agricultural centre of Turkey. In this context, monthly averages of meteorological variables, i.e. maximum and minimum temperature; sunshine duration; wind speed; and average, maximum, and minimum relative humidity, are used as inputs. Two different kernel-based methods, i.e. Gaussian process regression (GPR) and support vector regression (SVR), together with a Broyden–Fletcher–Goldfarb–Shanno artificial neural network (BFGS-ANN) and long short-term memory (LSTM) models were used to estimate ET0 amounts in 10 different combinations. The results showed that all four methods predicted ET0 amounts with acceptable accuracy and error levels. The BFGS-ANN model showed higher success (R2=0.9781) than the others. In kernel-based GPR and SVR methods, the Pearson VII function-based universal kernel was the most successful (R2=0.9771). Scenario 5, with temperatures including average temperature, maximum and minimum temperature, and sunshine duration as inputs, gave the best results. The second best scenario had only the sunshine duration as the input to the BFGS-ANN, which estimated ET0 having a correlation coefficient of 0.971 (Scenario 8). Conclusively, this study shows the better efficacy of the BFGS in ANNs for enhanced performance of the ANN model in ET0 estimation for drought-prone arid and semi-arid regions.

Download Full-text

Comparative analysis of Kernel-based versus BFGS-ANN and deep learning methods in monthly reference evaporation estimation

10.5194/hess-2020-224 ◽

2020 ◽

Author(s):

Mohammad Taghi Sattari ◽

Halit Apaydin ◽

Shahab Shamshirband ◽

Amir Mosavi

Keyword(s):

Deep Learning ◽

Minimum Temperature ◽

Meteorological Parameters ◽

Short Term Memory ◽

Sunshine Duration ◽

Gaussian Process Regression ◽

Support Vector ◽

Ann Model ◽

Learning Methods ◽

Average Maximum

Abstract. Proper estimation of the reference evapotranspiration (ET0) amount is an indispensable matter for agricultural water management in the efficient use of water. The aim of study is to estimate the amount of ET0 with a different machine and deep learning methods by using minimum meteorological parameters in the Corum region which is an arid and semi-arid climate with an important agricultural center of Turkey. In this context, meteorological variables of average, maximum and minimum temperature, sunshine duration, wind speed, average, maximum, and minimum relative humidity are used as input data monthly. Two different kernel-based (Gaussian Process Regression (GPR) and Support Vector Regression (SVR)) methods, BFGS-ANN and Long short-term memory models were used to estimate ET0 amounts in 10 different combinations. According to the results obtained, all four methods used predicted ET0 amounts in acceptable accuracy and error levels. BFGS-ANN model showed higher success than the others. In kernel-based GPR and SVR methods, Pearson VII function-based universal kernel was the most successful kernel function. Besides, the scenario that is related to temperature in all scenarios used, including average temperature, maximum and minimum temperature, and sunshine duration gave the best results. The second-best scenario was the one that covers only the sunshine duration. In this case, the ANN (BFGS-ANN) model, which is optimized with the BFGS method that uses only the sunshine duration, can be estimated with the 0.971 correlation coefficient of ET0 without the need for other meteorological parameters.

Download Full-text

Integrating genetic algorithm and support vector machine for modeling daily reference evapotranspiration in a semi-arid mountain area

Hydrology Research ◽

10.2166/nh.2016.205 ◽

2016 ◽

Vol 48 (5) ◽

pp. 1177-1191 ◽

Cited By ~ 22

Author(s):

Zhenliang Yin ◽

Xiaohu Wen ◽

Qi Feng ◽

Zhibin He ◽

Songbing Zou ◽

...

Keyword(s):

Genetic Algorithm ◽

Support Vector Machine ◽

Air Temperature ◽

Reference Evapotranspiration ◽

Accurate Estimation ◽

Support Vector ◽

Climatic Data ◽

Neural Network Models ◽

Mountain Area ◽

Semi Arid

Accurate estimation of evapotranspiration is vitally important for management of water resources and environmental protection. This study investigated the accuracy of integrating genetic algorithm and support vector machine (GA-SVM) models using climatic variables for simulating daily reference evapotranspiration (ET0). The developed GA-SVM models were tested using the ET0 calculated by Penman–Monteith FAO-56 (PMF-56) equation in a semi-arid environment of Qilian Mountain, northwest China. Eight models were developed using different combinations of daily climatic data including maximum air temperature (Tmax), minimum air temperature (Tmin), wind speed (U2), relative humidity (RH), and solar radiation (Rs). The accuracy of the models was evaluated using root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (r). The results indicated that the GA-SVM models successfully estimated ET0 with those obtained by the PMF-56 equation in the semi-arid mountain environment. The model with input combinations of Tmin, Tmax, U2, RH, and Rs had the smallest value of the RMSE and MAE as well as higher value of r (0.995) compared to other models. Relative to the performance of support vector machine (SVM) models and feed-forward artificial neural network models, it was found that the GA-SVM models proved superior for simulating ET0.

Download Full-text

Forecasting the risk at infractions: an ensemble comparison of machine learning approach

Industrial Management & Data Systems ◽

10.1108/imds-10-2020-0603 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Lei Li ◽

Desheng Wu

Keyword(s):

Machine Learning ◽

Prediction Models ◽

Short Term Memory ◽

Model Performance ◽

Large Data ◽

Support Vector ◽

Learning Approaches ◽

Content Type ◽

Day To Day Operations ◽

Prediction Approach

PurposeThe infraction of securities regulations (ISRs) of listed firms in their day-to-day operations and management has become one of common problems. This paper proposed several machine learning approaches to forecast the risk at infractions of listed corporates to solve financial problems that are not effective and precise in supervision.Design/methodology/approachThe overall proposed research framework designed for forecasting the infractions (ISRs) include data collection and cleaning, feature engineering, data split, prediction approach application and model performance evaluation. We select Logistic Regression, Naïve Bayes, Random Forest, Support Vector Machines, Artificial Neural Network and Long Short-Term Memory Networks (LSTMs) as ISRs prediction models.FindingsThe research results show that prediction performance of proposed models with the prior infractions provides a significant improvement of the ISRs than those without prior, especially for large sample set. The results also indicate when judging whether a company has infractions, we should pay attention to novel artificial intelligence methods, previous infractions of the company, and large data sets.Originality/valueThe findings could be utilized to address the problems of identifying listed corporates' ISRs at hand to a certain degree. Overall, results elucidate the value of the prior infraction of securities regulations (ISRs). This shows the importance of including more data sources when constructing distress models and not only focus on building increasingly more complex models on the same data. This is also beneficial to the regulatory authorities.

Download Full-text

A Machine Learning View on Momentum and Reversal Trading

Algorithms ◽

10.3390/a11110170 ◽

2018 ◽

Vol 11 (11) ◽

pp. 170 ◽

Cited By ~ 2

Author(s):

Zhixi Li ◽

Vincent Tam

Keyword(s):

Neural Network ◽

Machine Learning ◽

Stock Market ◽

Short Term Memory ◽

Predictive Ability ◽

Trading Strategies ◽

Machine Learning Techniques ◽

Support Vector ◽

Learning Approaches ◽

Learning Techniques

Momentum and reversal effects are important phenomena in stock markets. In academia, relevant studies have been conducted for years. Researchers have attempted to analyze these phenomena using statistical methods and to give some plausible explanations. However, those explanations are sometimes unconvincing. Furthermore, it is very difficult to transfer the findings of these studies to real-world investment trading strategies due to the lack of predictive ability. This paper represents the first attempt to adopt machine learning techniques for investigating the momentum and reversal effects occurring in any stock market. In the study, various machine learning techniques, including the Decision Tree (DT), Support Vector Machine (SVM), Multilayer Perceptron Neural Network (MLP), and Long Short-Term Memory Neural Network (LSTM) were explored and compared carefully. Several models built on these machine learning approaches were used to predict the momentum or reversal effect on the stock market of mainland China, thus allowing investors to build corresponding trading strategies. The experimental results demonstrated that these machine learning approaches, especially the SVM, are beneficial for capturing the relevant momentum and reversal effects, and possibly building profitable trading strategies. Moreover, we propose the corresponding trading strategies in terms of market states to acquire the best investment returns.

Download Full-text

Heuristic methods applied in reference evapotranspiration modeling

Ciência e Agrotecnologia ◽

10.1590/1413-70542018423006818 ◽

2018 ◽

Vol 42 (3) ◽

pp. 314-324 ◽

Cited By ~ 5

Author(s):

Daniel Althoff ◽

Helizani Couto Bazame ◽

Roberto Filgueiras ◽

Santos Henrique Brant Dias

Keyword(s):

Reference Evapotranspiration ◽

Performance Criteria ◽

Superior Performance ◽

Weather Data ◽

Coefficient Of Determination ◽

Accurate Estimation ◽

Support Vector ◽

Computational Techniques ◽

Heuristic Methods ◽

Scarce Data

ABSTRACT The importance of the precise estimation of evapotranspiration is directly related to sustainable water usage. Since agriculture represents 70% of Brazil’s water consumption, adequate and efficient application of water may reduce the conflicts over the use of water among the multiple users. Considering the importance of accurate estimation of evapotranspiration, the objective of the present study was to model and compare the reference evapotranspiration from different heuristic methodologies. The standard Penman-Monteith method was used as reference for evapotranspiration, however, to evaluate the heuristic methodologies with scarce data, two widely known methods had their performances assessed in relation to Penman-Monteith. The methods used to estimate evapotranspiration from scarce data were Priestley-Taylor and Thornthwaite. The computational techniques Stepwise Regression (SWR), Random Forest (RF), Cubist (CB), Bayesian Regularized Neural Network (BRNN) and Support Vector Machines (SVM) were used to estimate evapotranspiration with scarce and full meteorological data. The results show the robustness of the heuristic methods in the prediction of the evapotranspiration. The performance criteria of machine learning methods for full weather data varied from 0.14 to 0.22 mm d-1 for mean absolute error (MAE), from 0.21 to 0.29 mm d-1 for root mean squared error (RMSE) and from 0.95 to 0.99 coefficient of determination (r²). The computational techniques proved superior performance to established methods in literature, even in scenarios of scarce variables. The BRNN presented the best performance overall.

Download Full-text

Sentiment Analysis of Lithuanian Texts Using Traditional and Deep Learning Approaches

Computers ◽

10.3390/computers8010004 ◽

2019 ◽

Vol 8 (1) ◽

pp. 4 ◽

Cited By ~ 4

Author(s):

Jurgita Kapočiūtė-Dzikienė ◽

Robertas Damaševičius ◽

Marcin Woźniak

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Sentiment Analysis ◽

Short Term Memory ◽

Machine Learning Techniques ◽

Support Vector ◽

Learning Approaches ◽

Full Dataset ◽

Learning Techniques ◽

Long Short Term Memory

We describe the sentiment analysis experiments that were performed on the Lithuanian Internet comment dataset using traditional machine learning (Naïve Bayes Multinomial—NBM and Support Vector Machine—SVM) and deep learning (Long Short-Term Memory—LSTM and Convolutional Neural Network—CNN) approaches. The traditional machine learning techniques were used with the features based on the lexical, morphological, and character information. The deep learning approaches were applied on the top of two types of word embeddings (Vord2Vec continuous bag-of-words with negative sampling and FastText). Both traditional and deep learning approaches had to solve the positive/negative/neutral sentiment classification task on the balanced and full dataset versions. The best deep learning results (reaching 0.706 of accuracy) were achieved on the full dataset with CNN applied on top of the FastText embeddings, replaced emoticons, and eliminated diacritics. The traditional machine learning approaches demonstrated the best performance (0.735 of accuracy) on the full dataset with the NBM method, replaced emoticons, restored diacritics, and lemma unigrams as features. Although traditional machine learning approaches were superior when compared to the deep learning methods; deep learning demonstrated good results when applied on the small datasets.

Download Full-text

Global comparison of 20 reference evapotranspiration equations in a semi-arid region of Iran

Hydrology Research ◽

10.2166/nh.2018.174 ◽

2018 ◽

Vol 50 (1) ◽

pp. 282-300 ◽

Cited By ~ 10

Author(s):

Hadi Farzanpour ◽

Jalal Shiri ◽

Ali Ashraf Sadraddini ◽

Slavisa Trajkovic

Keyword(s):

Arid Region ◽

Reference Evapotranspiration ◽

Meteorological Data ◽

Irrigation Scheduling ◽

Climatic Conditions ◽

Accurate Estimation ◽

Management Scenarios ◽

Global Comparison ◽

Semi Arid Region ◽

Semi Arid

Abstract Accurate estimation of reference evapotranspiration (ETo) is a major task in hydrology, water resources management, irrigation scheduling and determining crop water requirement. There are many empirical equations suggested by numerous references in literature for calculating ETo using meteorological data. Some such equations have been developed for specific climatic conditions while some have been applied universally. The potential for usage of these equations depends on the availability of necessary meteorological parameters for calculating ETo in different climate conditions. The focus of the present study was a global cross-comparison of 20 ETo estimation equations using daily meteorological records of 10 weather stations (covering a period of 12 years) in a semi-arid region of Iran. Two data management scenarios, namely local and cross-station scenarios, were adopted for calibrating the applied equations against the standard FAO56-PM model. The obtained results revealed that the cross-station calibration might be a good alternative for local calibration of the ETo models when proper similar stations are used for feeding the calibration matrix.

Download Full-text

Forecasting CDS Term Structure Based on Nelson–Siegel Model and Machine Learning

Complexity ◽

10.1155/2020/2518283 ◽

2020 ◽

Vol 2020 ◽

pp. 1-23

Author(s):

Won Joong Kim ◽

Gunho Jung ◽

Sun-Yong Choi

Keyword(s):

Machine Learning ◽

Term Structure ◽

Short Term Memory ◽

Support Vector ◽

Group Method ◽

Learning Approaches ◽

Model Driven ◽

Forecasting Performance ◽

Interest Rate Term Structure ◽

The Interest Rate

In this study, we analyze the term structure of credit default swaps (CDSs) and predict future term structures using the Nelson–Siegel model, recurrent neural network (RNN), support vector regression (SVR), long short-term memory (LSTM), and group method of data handling (GMDH) using CDS term structure data from 2008 to 2019. Furthermore, we evaluate the change in the forecasting performance of the models through a subperiod analysis. According to the empirical results, we confirm that the Nelson–Siegel model can be used to predict not only the interest rate term structure but also the CDS term structure. Additionally, we demonstrate that machine-learning models, namely, SVR, RNN, LSTM, and GMDH, outperform the model-driven methods (in this case, the Nelson–Siegel model). Among the machine learning approaches, GMDH demonstrates the best performance in forecasting the CDS term structure. According to the subperiod analysis, the performance of all models was inconsistent with the data period. All the models were less predictable in highly volatile data periods than in less volatile periods. This study will enable traders and policymakers to invest efficiently and make policy decisions based on the current and future risk factors of a company or country.

Download Full-text

Improvement of ANN Models via Data Envelopment Analysis for Stock Prices Forecasting

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i4.10.20913 ◽

2018 ◽

Vol 7 (4.10) ◽

pp. 282

Author(s):

Raja Das ◽

Jitendra Kumar Jaiswal ◽

. .

Keyword(s):

Data Envelopment Analysis ◽

Hybrid Model ◽

Stock Prices ◽

Model Fitting ◽

Principal Component ◽

Support Vector ◽

Data Envelopment ◽

Learning Approaches ◽

Ann Model ◽

Ann Models

The implementation of artificial neural network techniques has become quite prevalent in the field of nonlinear data modelling and forecasting in this era. The only application of ANN models for model fitting may not be sufficient for close and satisfactory performances; hence the researchers are adopting hybrid models of ANN with different statistical and machine learning approaches such as support vector machines, particle sworm optimization, principal component analysis, etc. We have also developed a hybrid model in this paper with ANN and data envelopment analysis (DEA) techniques for stock prices forecasting in share market. The efficient decision making units have been selected with help of DEA approach and provided it as input to the Lavenberg-Marquardt technique based ANN model in sliding window manner. Further a closed performance of our hybrid model has been achieved by carrying out our experimentation with different number of nodes in the hidden layer of ANN model. Since the prices of stocks follow numerous factors such as demand and supply, political environments, economy and finance, buy and sell, etc., the historical prices for stocks may be convenient for the further forecasting.

Download Full-text

Flood Detection Using Multi-Modal and Multi-Temporal Images: A Comparative Study

Remote Sensing ◽

10.3390/rs12152455 ◽

2020 ◽

Vol 12 (15) ◽

pp. 2455

Author(s):

Kazi Aminul Islam ◽

Mohammad Shahab Uddin ◽

Chiman Kwan ◽

Jiang Li

Keyword(s):

Domain Adaptation ◽

Human Life ◽

Ground Truth ◽

Accurate Estimation ◽

Support Vector ◽

Learning Approaches ◽

Radar Images ◽

Response Team ◽

Multi Temporal ◽

Flood Detection

Natural disasters such as flooding can severely affect human life and property. To provide rescue through an emergency response team, we need an accurate flooding assessment of the affected area after the event. Traditionally, it requires a lot of human resources to obtain an accurate estimation of a flooded area. In this paper, we compared several traditional machine-learning approaches for flood detection including multi-layer perceptron (MLP), support vector machine (SVM), deep convolutional neural network (DCNN) with recent domain adaptation-based approaches, based on a multi-modal and multi-temporal image dataset. Specifically, we used SPOT-5 and RADAR images from the flood event that occurred in November 2000 in Gloucester, UK. Experimental results show that the domain adaptation-based approach, semi-supervised domain adaptation (SSDA) with 20 labeled data samples, achieved slightly better values of the area under the precision-recall (PR) curve (AUC) of 0.9173 and F1 score of 0.8846 than those by traditional machine approaches. However, SSDA required much less labor for ground-truth labeling and should be recommended in practice.

Download Full-text