Drought Modelling Based on Artificial Intelligence and Neural Network Algorithms: A Case Study in Queensland, Australia

The goal of this study is to compare the forecasting performance of classical artificial neural network and the hybrid model of artificial neural network and genetic algorithm. The time series data used is the monthly gold price per troy ounce in USD from year 1987 to 2016. A conventional artificial neural network trained by back propagation algorithm and the hybrid forecasting model of artificial neural network and genetic algorithms are proposed. Genetic algorithm is used to optimize the of artificial neural network neurons. Three forecasting accuracy measures which are mean absolute error, root mean squared error and mean absolute percentage error are used to compare the accuracy of artificial neural network forecasting and hybrid of artificial neural network and genetic algorithm forecasting model. Fitness of the model is compared by using coefficient of determination. The hybrid model of artificial neural network is suggested to be used as it is outperformed the classical artificial neural network in the sense of forecasting accuracy because its coefficient of determination is higher than conventional artificial neural network by 1.14%. The hybrid model of artificial neural network and genetic algorithms has better forecasting accuracy as the mean absolute error, root mean squared error and mean absolute percentage error is lower than the artificial neural network forecasting model.

A single hidden layer Artificial Neural Network (ANN) model was developed to estimate a machinery energy ratio (MER) indicator, used to characterize and assess mechanization status of potato farms in Iran with a view point of energy expenditure in farm machinery. A wide range of variables of farming activities were examined. Initially, 90 attributes were used as input variables to predict desired MER output. Using regression analysis, 13 inputs were finally selected to model MER. Performance of developed ANN model was evaluated with various statistical measures including the coefficient of determination (R2), mean absolute percentage error (MAPE), mean squared error (MSE) and mean absolute error (MAE). The optimum ANN model had a 13 - 4 - 1 configuration. The values of the optimum model’s outputs correlated well, with R2 of 0.98. Value of MAPE calculated as 0.0001 for best ANN model, which indicate superiority of this model over other prediction models. Sensitivity analyses were also conducted to investigate the effects of each input item on the output value. Since the ANN model can predict this mechanization indicator for a target farming system in Hamadan province of Iran, it could be a good estimator for appraising mechanization of other regional farms. Also it overcomes some of the limitations of using simple data available from local databases as inputs that may contain errors. Key words: Potato, agricultural mechanization, machinery energy ratio, Artificial Neural Network.

Chapter 2 - Modeling wheat yield with data-intelligent algorithms: artificial neural network versus genetic programming and minimax probability machine regression

Quality prediction and rivet/die selection for SPR joints with artificial neural network and genetic algorithm

Prediction of wind drift and evaporation losses from sprinkler irrigation using neural network and multiple regression techniques

Developing accurate drought prediction models for drought risk assessment and management, and comprehending their effectiveness is a challenging task. This study employed artificial neural network (ANN) and M5 model tree models to forecast two drought indices, i.e., one month timescale standardized precipitation index (SPI-1) and one month timescale standardized precipitation evapotranspiration index (SPEI-1) with one-month lead time for the middle Gujarat, India using 30-year (1986-2015) gridded dataset of rainfall and temperature. The models were developed considering one to twenty hidden neurons, and trained using Levenberg-Marquardt algorithm to minimize the prediction error. Log-sigmoidal transfer functions were applied in both the hidden and output layers. Of the total data (Jan 1986-Dec 2015), 70% data (Jan 1986-Dec 2006) were used for model training, 15% data (Jan 2007-Jun 2011) for cross-validation and remaining 15% data (Jul 2011 - Dec 2015) for model testing. Results indicated that prediction accuracy of SPI-1 was better than that of SPEI-1 at one-month lead time as revealed in terms of five performance indicators, namely, coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE), mean absolute error (MAE), and percentage peak deviation (Pdv). It was found that ANN model for each grid was having considerably different performance in forecasting SPI-1 and SPEI-1 with R2, NSE (%), RMSE, Pdv (%), and MAE having highest values as 0.693, 46.93, 0.844, 62.65, and 0.65, respectively, for SPI-1, whereas these were 0.469, 20.06, 1.07, 90.25, 0.87, respectively, for SPEI-1. It was revealed that performance of ANN models in forecasting SPI-1 was better in comparison to SPEI-1. Amongst ANN and M5 models, ANN models performed better than the M5 model tree for most of the grids selected in this study. Different ANN models with log sigmoidal activation function in the hidden as well as in the output layer for SPI-1 drought index forecast with one-month lead time were suggested for use by scientists, irrigation planners, and policy makers.

Non-destructive estimation of leaf area of durian (Durio zibethinus) – An artificial neural network approach

این مطالعه به منظور بررسی پیش بینی شاخص های عملکرد تولیدی در مرغان تخم گذار با استفاده از شبکه های عصبی مصنوعی و رگرسیون غیرخطی چندگانه انجام شد. بررسی بر روی اطلاعات چهار دوره متوالی پرورش در یک واحد پرورش مرغ تخم گذار صورت گرفت. روش های داده-کاوی شامل رگرسیون خطی و غیر خطی، شبکه عصبی پرسپترون سه لایه، شبکه عصبی پرسپترون چهار لایه و شبکه عصبی با تابع پایه ای شعاعی بود. در این مدل ها از متغیرهای سن گله، میزان خوراک مصرفی و فصل تولید به عنوان متغیر پیشگو و شاخص های عملکرد تولیدی شامل درصد تخم-گذاری، وزن توده ای تخم مرغ تولیدی و ضریب تبدیل غذایی به عنوان متغیر پاسخ استفاده شد. نتایج نهایی رگرسیون های خطی نشان داد که برای تمامی متغیرهای وابسته مورد مطالعه متغیر مستقل سن گله معنی دار می باشد. بنابراین رگرسیون غیر خطی شاخص های عملکرد تولیدی در مقابل سن برای مقایسه با شبکه های عصبی مختلف مورد بررسی قرار گرفت و برای مقایسه کلیه مدل ها از ضریب تعیین (R2) و میانگین قدر مطلق خطا (MAE) استفاده شد. نتایج نشان داد بین شبکه های عصبی مصنوعی مختلف مورد مطالعه، شبکه با تابع پایه ای شعاعی بهتر از سایر مدل های در پیش‌بینی شاخص های عملکرد تولیدی مرغان تخم گذار عمل می کند.

This paper presents the correlation between the predicted and desired/targeted thermal conductivity of food products as a function of moisture content, temperature and apparent density. The food products considered in this work are the bakery products which include bread, bread dough, cake, and whole-wheat dough. Statistical data of results from previous work in existing literatures were used in this work for a wide range of moisture contents, temperatures and apparent densities resulting from baking conditions. The results of this work showed straight line curves when the predicted values of thermal conductivity were plotted against the targeted values of thermal conductivity. This demonstrates correlation between the predicted and targeted thermal conductivities when the points are joined together (best fit-points), hence, a very good agreement between the predicted and the desired values of thermal conductivity. The two ANN models that were finally selected, after several configurations had been considered and evaluated, are the optimal ANN model that was found to be a network with two hidden layers and eight neurons and the simplest ANN model was equally found to be a network with one hidden layer and ten neurons. The estimated errors between the predicted and desired (or targeted) thermal conductivity values of the bakery products for both the optimal ANN and simplest ANN models are the MRE, MAE and SE. Moreover, the results also showed that the optimal ANN model had an MRE of 0.04878%, an MAE of 0.0054W/mK and an SE of 0.0015W/mK while the simplest ANN model was estimated to have an MRE of 0.03388%, an MAE of 0.0034W/mK and an SE of 0.0011W/mK. These errors are approximately equal to zero (i.e., 0 W/mK) and could, therefore, be regarded as a good result for the prediction. Since the simplest ANN model had the least values of all three errors (MRE, MAE and SE) when compared with other configurations, including the optimal ANN model, it is, however, regarded as the best ANN model and is, thus, recommended.

Nowadays , nonlinear time series and artificial neural networks (ANN) models are used for forecasting in the field of business, agriculture and soon. Recent studies have shown, ANN have been successfully used for forecasting of financial and agriculture data series The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. ANN have more advantages that can approximate to model both linear and nonlinear structures in time series, they are not able to handling both structures equally well. The autoregressive integrated moving average (ARIMA) model and two ANN models namely, Radial basis function neural networks (RBFNN), and Elman recurrent neural networks (ERNN) methods were applied to Hyderabad airport traffic data. The data obtained for 15 years from 2002–2003 to 2016–2017 about domestic and international passenger of International Airport of Hyderabad, India. In this research paper, we compared the performances of ARIMA, RBFNN and ERNN were based on three measures: mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). The results showed that RBFNN obtained the smallest MAE, MAPE and RMSE in both the modeling and forecasting processes. The performances of the three models ranked in ascending order were: ARIMA, ERNN and the RBFNN model. Keywords: T ime series, forecasting, artificial neural networks, ARIMA models, radial basis function neural networks, and Elman recurrent neural networks Cite this Article R. Ramakrishna, Berhe Aregay, Tewodros Gebregergs. The Comparison in Time Series Forecasting of Air Traffic Data by Autoregressive Integrated Moving Average Model, Radial Basis Function and Elman Recurrent Neural Networks. Research & Reviews: Journal of Statistics . 2018; 7(3): 75–90p.

Renewable energy sources (RES) are being used and integrated into the electrical grid as a result of the environment’s effects and the ever-increasing demand for energy. Reliable and accurate forecasts are necessary to address environmental concerns and improve grid management due to the intermittent availability of renewable energy sources. This study focuses on improving ANN-based techniques for precise solar irradiance prediction as the prediction accuracy of an artificial neural network (ANN) is impacted by the random assignment of weights to its edges. As a result, we proposed hybrid solar irradiance forecasting models in which the cuckoo search algorithm (CSA) and adaptive moment estimation (ADAM) are used to optimize the weights assigned to the ANN’s edges. Two models were presented in this study namely: ADAM-optimized ANN model and a novel two-stage optimization technique known as CSA-ADAM optimized ANN model for accurate and reliable forecasting of solar irradiance. Both models were tested using actual weather data, and standard error metrics like mean squared error (MSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean square error (RMSE) to assess their accuracy. The outcomes demonstrate that ADAM-optimized ANN model produced MSE = 0.52, MAPE = 0.18%, MAE = 0.64, and RMSE = 0.72, and CSA-ADAM optimized ANN model obtained MSE = 0.25, MAPE = 0.17%, MAE = 0.43, and RMSE = 0.50. We evaluated the practicality of both models by comparing their average prediction times using the same test dataset. While the ADAM-optimized ANN model took an average of 0.1093 ± 0.0085 seconds to make predictions on the test data, the CSA-ADAM optimized ANN model took 0.1110 ± 0.0058 seconds. These findings demonstrate that using CSA to optimize the ANN weights increases the accuracy of solar irradiance predictions.

Fly-rock induced by blasting is an undesirable phenomenon in quarries. It can be dangerous for humans, equipment, and buildings. To minimize its undesirable hazards, we proposed a state-of-the-art technology of fly-rock prediction based on artificial neural network (ANN) models and their robust combination, called EANNs model (ensemble of ANN models); 210 fly-rock events were recorded to develop and test the ANN and EANNs models. Of thi sample, 80% of the whole dataset was assigned to develop the models, the remaining 20% was assigned to confirm the models developed. Accordingly, five ANN models were designed and developed using the training dataset (i.e., 80% of the whole original data) first; then, their predictions on the training dataset were ensembled to generate a new training dataset. Subsequently, another ANN model was developed based on the new set of training data (i.e., EANNs model). Its performance was evaluated through a variety of performance indices, such as MAE (mean absolute error), MAPE (mean absolute percentage error), RMSE (root-mean-square error), R2 (correlation coefficient), and VAF (variance accounted for). A promising result was found for the proposed EANNs model in predicting blast-induced fly-rock with a MAE = 2.777, MAPE = 0.017, RMSE = 4.346, R2 = 0.986, and VAF = 98.446%. To confirm the performance of the proposed EANNs model, another ANN model with the same structure was developed and tested on the training and testing datasets. The findings also indicated that the proposed EANNs model yielded better performance than those of the ANN model with the same structure.

As monitoring of spray drift during application can be expensive, time-consuming, and labor-intensive, drift predicting models may provide a practical complement. Several mechanistic models have been developed as drift prediction tool for various types of application equipment. Nevertheless, mechanistic models are quite often intricate and complex with a large number of input parameters required. Quite often, the detailed data needed for such models are not readily available. In this study, two advanced machine learning models (artificial neural network (ANN) and support vector regression (SVR)) were developed for pesticide drift prediction and compared with three conventional regression-based models: multiple linear regression (MLR), generalized linear model (GLM), and generalized nonlinear least squares (GNLS). The models were evaluated in fivefold cross-validation and by external validation using the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and mean absolute bias (MAB). From regression-based models, GLM and GNLS models performed very well when evaluated by cross-validation with R2 = 0.96 and 0.95 and RMSE = 0.70 and 0.82 respectively, while MLR performed less with R2 of 0.65 and RMSE of 2.25. Simultaneously, ANN and SVR models performed very well with R2 = 0.98 and 0.97 and RMSE = 0.58 and 0.71 respectively. Overall, ANN model performed best compared to the other four models followed by SVR. A comparison was also made between the high-performing model, ANN, and two previously published empirical models. The ANN model outperformed the two previously published empirical models and can be used to predict pesticide drift. Therefore, the ANN model is a potentially promising new approach for predicting ground drift that merits further study. In conclusion, our work demonstrated that the new approach, ANN and SVR-based models, for pesticide drift modeling has better predictive power than conventional regression models. Their ability to model complex relationships is a clear benefit in pesticide drift modeling where the variability in pesticide drift is often affected by a number of variables and the relationships between drift and predictors are very complicated. We believe such insights will pave better way for the application of machine learning towards spray drift modeling.

Wavelet regression model for short-term streamflow forecasting

In this paper, an optimal model is developed for path loss predictions using the Feed-Forward Neural Network (FFNN) algorithm. Drive test measurements were carried out in Canaanland Ota, Nigeria and Ilorin, Nigeria to obtain path loss data at varying distances from 11 different 1,800 MHz base station transmitters. Single-layered FFNNs were trained with normalized terrain profile data (longitude, latitude, elevation, altitude, clutter height) and normalized distances to produce the corresponding path loss values based on the Levenberg–Marquardt algorithm. The number of neurons in the hidden layer was varied (1–50) to determine the Artificial Neural Network (ANN) model with the best prediction accuracy. The performance of the ANN models was evaluated based on different metrics: Mean Absolute error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), standard deviation, and regression coefficient (R). Results of the machine learning processes show that the FNN architecture adopting a tangent activation function and 48 hidden neurons produced the least prediction error, with MAE, MSE, RMSE, standard deviation, and R values of 4.21 dB, 30.99 dB, 5.56 dB, 5.56 dB, and 0.89, respectively. Regarding generalization ability, the predictions of the optimal ANN model yielded MAE, MSE, RMSE, standard deviation, and R values of 4.74 dB, 39.38 dB, 6.27 dB, 6.27 dB, and 0.86, respectively, when tested with new data not previously included in the training process. Compared to the Hata, COST 231, ECC-33, and Egli models, the developed ANN model performed better in terms of prediction accuracy and generalization ability.