Search

This paper proposes a comparison of various time series forecasting models to forecast annual data on sugarcane production over 63 years from 1960 to 2022. In this research, the Mean Forecast Model, the Naive Model, the Simple Exponential Smoothing Model, Holt's model, and the Autoregressive Integrated Moving Average time series models have all been used to make effective and accurate predictions for sugarcane. Different scale‐dependent error forecasting techniques and residual analysis have been used to examine the forecasting accuracy of these time series models. SE of Residuals, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Akaike's Information Criterion (AIC) are used to analyse the forecast's accuracy. The best model has been selected based on the predictions with the lowest value, according to the three‐performance metrics of RMSE, MAE, and AIC. The estimated sugarcane production shows an increasing trend for the next 10 years and is projected to be 37,763.38 million tonnes in the year 2032. Further, empirical results support the plan and execution of viable strategies to advance sugarcane production in India to fulfil the utilisation need of the increasing population and further improve food security. [ABSTRACT FROM AUTHOR]

Solar photovoltaic (PV) power is emerging as one of the most viable renewable energy sources. The recent enhancements in the integration of renewable energy sources into the power grid create a dire need for reliable solar power forecasting techniques. In this paper, a new long‐term solar PV power forecasting approach using long short‐term memory (LSTM) model with Nadam optimizer is presented. The LSTM model performs better with the time‐series data as it persists information of more time steps. The experimental models are realized on a 250.25 kW installed capacity solar PV power system located at MANIT Bhopal, Madhya Pradesh, India. The proposed model is compared with two time‐series models and eight neural network models using LSTM with different optimizers. The obtained results using LSTM with Nadam optimizer present a significant improvement in the forecasting accuracy of 30.56% over autoregressive integrated moving average, 47.48% over seasonal autoregressive integrated moving average, and 1.35%, 1.43%, 3.51%, 4.88%, 11.84%, 50.69%, and 58.29% over models using RMSprop, Adam, Adamax, SGD, Adagrad, Adadelta, and Ftrl optimizer, respectively. The experimental results prove that the proposed methodology is more conclusive for solar PV power forecasting and can be employed for enhanced system planning and management. [ABSTRACT FROM AUTHOR]

Steady‐state forecasting is indispensable for power system planning and operation. A forecasting model for inputs considering their historical record is a preliminary step for such type of studies. Since the historical data quality is decisive in edifice an accurate forecasting model, data preprocessing is essential. Primarily, the quality of raw data is affected by the presence of outliers, and preprocessing refers to outlier detection and correction. In this paper, an effort is made to improve the existing sliding window prediction‐based preprocessing method. The recommended reforms are the calculation of appropriate window width and a new outlier correction approach. The proposed method denoted as improved sliding window prediction‐based preprocessing is applied to the historical data of PV generation, load power, and the ambient temperature of different time‐steps collected from various places in the United States and India. Firstly, the method's efficacy through detailed result analysis demonstrating the proposed preprocessing as a better way than its precursor and k‐nearest neighbor approach is presented. Later, the improved out‐of‐sample forecasting accuracy canonizes the proposed method's concert compared to both the above techniques and the case without preprocessing. [ABSTRACT FROM AUTHOR]

Abstract This paper describes a methodology by which modelers, ecologists and planners can quantify the certainty in predicting the location of change for a given quantity of change. The specification of the quantity of a land cover category and the specification of the location of a land cover category are two distinct fundamental concepts in geographical analysis. It is crucial that scientists have appropriate quantitative tools to analyze each of these two concepts independently of one another. This paper gives methods whereby a scientist can convert a map of relative propensity for disturbance to a map of probability of future disturbance, based on a quantifiable validation of a map's predictive ability. The required inputs are: (1) maps that show a Boolean categorical variable at times 0, 1 and 2, (2) a technique to create a map that shows the relative propensity for membership in the Boolean category, and (3) a predicted proportion of the category at time 3. [ABSTRACT FROM AUTHOR]

Rice is the staple food in many countries and is grown in varied climates from per-humid to semiarid areas. Crop–weather models were used to predict rice yield in India. However, in spite of a significant influence of solar radiation on rice yield, none of these models used solar radiation as one of the predictors. In this paper, an attempt was made to predict the first season (June–September) rice yield at Coimbatore, Tamil Nadu, India by including solar radiation as one of the predictors. Ten years (1987/88–1996/97) data were used for the study. Seven predictors viz., percentage of rice area during first season (X1 ), number of days with minimum temperature below 22 °C in August and September (X2 ), average daily maximum temperature for three months (July, August and September; X3 ), average daily minimum temperature for three months (July, August and September; X4 ), total of average sunshine hours in August and September (X5 ), and total rainfall of July, August and September (X6 ) total average solar radiation of August and September (X7 ) were selected based on earlier report. Full model and stepwise regression analysis were performed using MSTAT computer package. The full model regression without solar radiation as predictor (Model I) recorded comparatively less R2 (0.6292). Inclusion of solar radiation (Model II) enhanced the R2 value considerably (R2 =0.9464). Seven variables were further subjected to stepwise regression analysis and only four predictors were retained in the final model (Model III) with an R2 value of 0.9234. The model III with minimum parameters Y=22119.5758 + 19.6898, X1 - 150.9261, X2 - 1126.7501, X4 + 0.7179 X7 can be used to predict the first season rice yield (Y) at Coimbatore, India. [ABSTRACT FROM AUTHOR]