scholarly journals A study on recent changes in weekly evaporation at selected locations in India

MAUSAM ◽  
2021 ◽  
Vol 59 (2) ◽  
pp. 211-218
Author(s):  
I. J. VERMA ◽  
H. P. DAS ◽  
V. N. JADHAV
Keyword(s):  
Time Series ◽  
Coefficient Of Variation ◽  
Time Series Data ◽  
Linear Trend ◽  
Series Data ◽  
Evaporation Time ◽  
Statistical Parameters ◽  
Analysis Technique ◽  
Minimum Number ◽  
Almost All

Thirty years evaporation time series data (1971-2000) recorded from US class-A evaporation pans for ten well distributed locations in India, have been utilized in the present study. For these locations, basic statistical parameters of weekly evaporation [minimum, maximum, range, mean, standard deviation (S.D.) and coefficient of variation (C.V.)] have been computed. Variations in average weekly evaporation in different weeks and at different locations have been plotted and discussed. Changes in weekly evaporation have been studied using linear trend analysis technique on weekly evaporation time series data for standard meteorological weeks (1 to 52). Graphs have been plotted, for all ten different locations, to study week wise distribution of changes in weekly evaporation trends and to identify the specific periods when significant changes occur.   The highest average weekly evaporation of 107.5 mm has been observed at Jodhpur in standard week                    21(21 – 27 May). The lowest average weekly evaporation of 14.5 mm has been observed at Karimganj in standard week 3 (15 – 21 January). The peak in average weekly evaporation, at most of these locations is achieved around standard week   20 (14 – 20 May). The coefficient of variation (C.V.) at these locations varied between 18.7 and 51.8 percent. The highest C.V. of 51.8 % has been observed at Bikramganj, whereas the lowest C.V. of 18.7 % has been observed at Rajamundry. Out of 52 weeks, Pune and Rajamundry have shown significant decreasing trend in weekly evaporation in maximum number of weeks (37) and Bhubaneshwar has shown significant decreasing trend in weekly evaporation in minimum number of weeks (10). At six locations (Bikramganj, Hissar, Jodhpur, Pattambi, Pune and Rajamundry), the number of weeks showing significant decreasing trend in weekly evaporation have been found to be more than 23 weeks. At more than five locations significant decreasing trend in weekly evaporation occur, in almost all weeks, between standard weeks 1 to 19 (1 January - 13 May) and also between standard weeks 40 to 52 (1 October - 31 December). In almost all the locations, significant decreasing trend in weekly evaporation occur, in standard week numbers 1-2, 9-10, 13 and 15.

scholarly journals Recent variations and trends in pan evaporation over India

MAUSAM ◽  
2021 ◽  
Vol 59 (3) ◽  
pp. 347-356
Author(s):  
I. J. VERMA ◽  
V. N. JADHAV
Keyword(s):  
Time Series Data ◽  
Linear Trend ◽  
Series Data ◽  
Pan Evaporation ◽  
Statistical Parameters ◽  
Class A ◽  
Linear Relationships ◽  
Analysis Technique ◽  
Annual Evaporation ◽  
The Mean

Thirty years pan evaporation time series data (1971-2000) recorded from US class-A evaporation pans for twenty well distributed locations in India, have been utilized in the present study. For all the locations, basic statistical parameters of annual evaporation [minimum, maximum, range, mean, standard deviation (S.D.) and coefficient of variation (C.V.)] have been computed. Annual, seasonal and monthly trends have been studied using linear trend analysis technique. Suitable graphs have been plotted to study the variations and changes in pan evaporation trends and to identify the specific periods as and when significant changes occur.   The mean annual pan evaporation was found to be lowest (1107 mm) at Buralikson and highest (3004 mm) at Rajkot. The highest C.V. of nearly 11% was observed at Rajamundry, Jodhpur, Buralikson and Nellore. The lowest C.V. of nearly 2% was observed at Ambikapur. Out of twenty locations, significant decreasing trend in annual pan evaporation was observed at fifteen locations and no significant trend at five locations. The annual dE/dt values varied from -6.27 (Canning) to -29.30 (Jodhpur) mm/year. The average annual dE/dt over India was found to be -14.90 mm/year. Linear relationship was obtained to quantitatively estimate annual dE/dt, at a given location, using pan evaporation range. On an average, over India, the contribution of seasonal dE/dt towards annual dE/dt (mm/year) is highest -5.63 (37.8 %) in Season-2 (March-April-May) and lowest -2.07 (13.9 %) in Season-1(January- February). On an average, over India, the contribution of monthly dE/dt towards annual dE/dt (mm/year) is highest - 2.08 (14.0 %) in May and lowest -0.77 (5.2 %) in August. Non linear relationships were obtained (a) to quantitatively estimate the average monthly dE/dt values over India, in any particular month (b) to quantitatively estimate the average cumulative dE/dt values over India (mm/year) upto any particular month and (c) to quantitatively estimate the contribution (per cent) towards average annual dE/dt over India, upto any particular month.

scholarly journals Recent variations and trends in potential evapotranspiration (PET) over India

MAUSAM ◽  
2021 ◽  
Vol 59 (1) ◽  
pp. 119-128
Author(s):  
I. J. VERMA ◽  
V. N. JADHAV ◽  
ERANDE R. S.
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Potential Evapotranspiration ◽  
Linear Trend ◽  
Series Data ◽  
Linear Relationships ◽  
Analysis Technique ◽  
Linear Trend Analysis ◽  
The Mean ◽  
Monteith Equation

Thirty years meteorological time series data (1971-2000), for twenty two well distributed locations in India, have been utilized to compute potential evapotranspiration using FAO recommended Penman-Monteith equation. Annual, seasonal and monthly PET trends have been studied using linear trend analysis technique. Suitable graphs have been plotted to study the variations and changes in PET trends and to identify the specific periods as and when significant changes occur.                 The mean annual PET has been found to be lowest (1100 mm) at Buralikson and highest (2109 mm) at Bellary. Out of twenty two locations, significant decreasing trend in annual PET has been observed at seventeen locations and no significant trend at five locations. The mean annual dEo/dt over India has been found to be -9.36 mm/year. Linear relationship has been obtained to quantitatively estimate annual dEo/dt, at a given location, using annual PET range. Non linear relationships have been obtained (a) to quantitatively estimate the mean monthly dEo/dt values over India, (b) to quantitatively estimate the average cumulative dEo/dt values over India (mm/year) up to any particular month and (c) to quantitatively estimate the contribution (percent) towards average annual dEo/dt over India, up to any particular month.

scholarly journals System for Prediction of Non Stationary Time Series based on the Wavelet Radial Bases Function Neural Network Model

2018 ◽  
Vol 8 (4) ◽  
pp. 2327 ◽  
Author(s):  
Heni Kusdarwati ◽  
Samingun Handoyo
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Time Series Data ◽  
Linear Trend ◽  
Stationary Time Series ◽  
Series Data ◽  
Training Time ◽  
Stationary Time ◽  
Computation Process ◽  
Smooth Coefficients

This paper proposes and examines the performance of a hybrid model called the wavelet radial bases function neural networks (WRBFNN). The model will be compared its performance with the wavelet feed forward neural networks (WFFN model by developing a prediction or forecasting system that considers two types of input formats: input9 and input17, and also considers 4 types of non-stationary time series data. The MODWT transform is used to generate wavelet and smooth coefficients, in which several elements of both coefficients are chosen in a particular way to serve as inputs to the NN model in both RBFNN and FFNN models. The performance of both WRBFNN and WFFNN models is evaluated by using MAPE and MSE value indicators, while the computation process of the two models is compared using two indicators, many epoch, and length of training. In stationary benchmark data, all models have a performance with very high accuracy. The WRBFNN9 model is the most superior model in nonstationary data containing linear trend elements, while the WFFNN17 model performs best on non-stationary data with the non-linear trend and seasonal elements. In terms of speed in computing, the WRBFNN model is superior with a much smaller number of epochs and much shorter training time.

scholarly journals PENGARUH KUNJUNGAN WISATAWAN DAN RATA-RATA PENGELUARAN WISATAWAN TERHADAP PAD DAN PERTUMBUHAN EKONOMI PROVINSI BALI

2021 ◽  
pp. 511
Author(s):  
I Gede Dea Joendra Septyana Putra ◽  
Ni Luh Karmini ◽  
I Wayan Wenagama
Keyword(s):  
Economic Growth ◽  
Time Series ◽  
Time Series Data ◽  
Secondary Data ◽  
Data Sources ◽  
Series Data ◽  
Local Revenue ◽  
Analysis Technique ◽  
Secondary Data Sources

This study aims to analyze the effect of the number of tourist visits and the average tourist expenditure on the local income of Bali Province, to analyze the effect of the number of tourist visits, average tourist expenditure, and local income on the economic growth of Bali Province, and to analyze the role of income. native areas in mediating the effect of the number of tourist visits and the average tourist expenditure on the economic growth of Bali Province. The data used in this research is secondary data, with the method of observation by observing documents or secondary data sources that are related. This study uses time series data with a total of 30 years of observations from 1990-2019, with the analysis technique used is Path Analysis. This study shows the results that the number of tourist visits and the average tourist expenditure have a positive and significant effect on local income in Bali Province. The number of tourist visits, the average tourist expenditure and local revenue have a positive and significant effect on economic growth in Bali Province. Own-source revenue mediates the effect of the number of tourist visits and the average tourist expenditure on economic growth in Bali Province.

scholarly journals Eagle View: An Abstract Evaluation of Machine Learning Algorithms based on Data Properties

2021 ◽  
Author(s):  
Dhairya Vyas
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Time Series Data ◽  
Learning Algorithms ◽  
Numerical Data ◽  
Machine Learning Algorithms ◽  
Series Data ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Almost All

In terms of Machine Learning, the majority of the data can be grouped into four categories: numerical data, category data, time-series data, and text. We use different classifiers for different data properties, such as the Supervised; Unsupervised; and Reinforcement. Each Categorises has classifier we have tested almost all machine learning methods and make analysis among them.

scholarly journals A novel cross-validation strategy for artificial neural networks using distributed-lag environmental factors

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0244094
Author(s):  
Chao-Yu Guo ◽  
Tse-Wei Liu ◽  
Yi-Hau Chen
Keyword(s):  
Time Series ◽  
Cross Validation ◽  
Time Series Data ◽  
Series Data ◽  
Prediction Errors ◽  
Statistical Regression ◽  
Ann Model ◽  
Distributed Lag ◽  
Minimum Number ◽  
Artificial Neural

In recent years, machine learning methods have been applied to various prediction scenarios in time-series data. However, some processing procedures such as cross-validation (CV) that rearrange the order of the longitudinal data might ruin the seriality and lead to a potentially biased outcome. Regarding this issue, a recent study investigated how different types of CV methods influence the predictive errors in conventional time-series data. Here, we examine a more complex distributed lag nonlinear model (DLNM), which has been widely used to assess the cumulative impacts of past exposures on the current health outcome. This research extends the DLNM into an artificial neural network (ANN) and investigates how the ANN model reacts to various CV schemes that result in different predictive biases. We also propose a newly designed permutation ratio to evaluate the performance of the CV in the ANN. This ratio mimics the concept of the R-square in conventional statistical regression models. The results show that as the complexity of the ANN increases, the predicted outcome becomes more stable, and the bias shows a decreasing trend. Among the different settings of hyperparameters, the novel strategy, Leave One Block Out Cross-Validation (LOBO-CV), demonstrated much better results, and the lowest mean square error was observed. The hyperparameters of the ANN trained by the LOBO-CV yielded the minimum number of prediction errors. The newly proposed permutation ratio indicates that LOBO-CV can contribute up to 34% of the prediction accuracy.

scholarly journals Growth Model and Forecasting Prices of Some Agricultural Products in Bangladesh

2021 ◽  
Vol 26 (2) ◽  
pp. 64-71
Author(s):  
Md Hossain
Keyword(s):  
Time Series ◽  
Growth Model ◽  
Selection Criteria ◽  
Time Series Data ◽  
Linear Trend ◽  
Series Data ◽  
Percentage Error ◽  
Absolute Deviation ◽  
Trend Model ◽  
Exponential Method

The aim of this paper was to explore the appropriate deterministic time series model using the latest selection criteria considering the price pattern of onion, garlic and potato products in Bangladesh (January 2000 to December 2016). It appeared from our analysis that the time series data for the prices of potato was first order homogenous stationary but onion and garlic were found to be the second order stationary. Four different forecasting models namely, linear trend model, quadratic trend model, exponential growth model, and S-curve trend model were used to find the best fitted model for the prices of above mentioned products in the Bangladesh. Three accuracy measures such as mean absolute percentage error (MAPE), mean absolute deviation (MAD) and mean squared deviation (MSD) were used for the selection of the best fitted model based on lowest value of forecasting error. Lowest values of these errors indicated a best fitted model. After choosing the best growth model by the latest model selection criteria, prices of selected agricultural commodities were forecasted using the following time-series analysis methods: Simple Exponential Method, Double Exponential Method using the time period from January 2017 to December 2021. The findings of this study would be useful for policy makers, researchers, businessmen as well as producers in order to forecast future prices of these commodities.

scholarly journals PENGARUH JUMLAH PERCEPATAN RESTITUSI PAJAK PERTAMBAHAN NILAI TERHADAP PENERIMAAN PAJAK PERTAMBAHAN NILAI (Studi pada Kantor Pelayanan Pajak Pratama Malang Utara)

Profit ◽  
2021 ◽  
Vol 15 (01) ◽  
pp. 120-129
Author(s):  
Astri Warih Anjarwi ◽  
Linda Kharisma
Keyword(s):  
Time Series ◽  
Data Analysis ◽  
Time Series Data ◽  
Value Added ◽  
Secondary Data ◽  
Variable Number ◽  
Series Data ◽  
Value Added Tax ◽  
Analysis Technique ◽  
The Cost

The Accelerated of Value Added Tax Restitution is Indonesian government’s policy to a preliminary refund of value added tax overpayment. The simplification or the acceleration of the provision of restitution is done without strict examination and long process, but by simple research. Accelerated restitution policy is given to the Taxpayer who fulfills certain requirements (certain amount of restitution as mentioned above), certain criteria (Taxpayers who comply) and they are low risk Taxable Entrepreneurs that determined by the Minister of Finance. The Acceleration of Value Added Tax restitution is expected to reduce the cost compliance because the provision of restitution is done without examination and it is hoped that this policy could increase cash flow and liquidity of the economy. The research’s purpose is determine to impact the number of acceleration of value added tax restitution to the acceptance of value added tax. The type of research is explanatory research with a quantitative approach. The research’s data is secondary data that obtaine from the Pratama Tax Office Malang Utara. The research’s data is time series data during the periode of April 2018 – November 2019. The data analysis technique on the research is a simple regresi linier analysis. The results of this research is variable number of acceleration restitution on value added tax impact and significant for the revenue value added tax in the Pratama Tax Office Malang Utara. The value of R Square earned is 0.374 which means that the number of accelerated restitution of value added tax has an impact on the variable revenue of value added tax is 37.4%.

Decomposition analysis and acreage response of pigeonpea in western Vidarbha

2016 ◽  
Author(s):  
M. Vikram Sandeep ◽  
S. S. Thakare ◽  
D. H. Ulemale
Keyword(s):  
Growth Rate ◽  
Time Series ◽  
Coefficient Of Variation ◽  
Time Series Data ◽  
Decomposition Analysis ◽  
Secondary Data ◽  
Pigeon Pea ◽  
Series Data ◽  
Response Analysis ◽  
Instability Index

In the present investigation, an attempt was made to study the decomposition and acreage response of pigeonpea in western Vidarbha. The study was based on time series secondary data on the rainfall, farm harvest prices and other data, which were obtained from various Government publications. Nerlovian lagged adjustment model (1958) was used in acreage response analysis based on time series data. The study revealed that the compound growth rate for area and production under pigeon pea was recorded high during period I in all the districts. During period II, the area, production and productivity of pigeonpea registered mostly negative growth rates in all the districts. During period III, the compound growth rate for area, production and productivity under pigeonpea has increased in all the districts of western Vidarbha region. At overall period, the coefficient of variation and Coppock's instability index for area, production and productivity were high for pigeonpea in Akola district compared to other districts and coefficient of variation and Coppock's instability index for production and productivity were lowest for pigeonpea in Amravati district. At overall period, in pigeonpea, the area effect (56.61%) was most responsible factor for increasing production in Amravati division with positive yield and interaction effect i.e. 18.91 per cent and 23.75 per cent respectively.

scholarly journals Penanganan Pencilan pada Peramalan Data Deret Waktu Menggunakan Metode Pemulusan Holt dan Robust Holt

2021 ◽  
Vol 10 (2) ◽  
pp. 112-128
Author(s):  
Septanti Kusuma Dwi Arini ◽  
Farit Mochamad Afendi ◽  
Pika Silvianti
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Linear Trend ◽  
Smoothing Method ◽  
Training Data ◽  
Series Data ◽  
Data Series ◽  
Absolute Deviation ◽  
Trend Data ◽  
Time Series Simulation

The time series data used is time series data following the LLTM (local linear trend model) model with four different error conditions. These conditions are Clean Data (CD), Symmetric Outliers (SO), Asymmetric Outliers (AO) and Fat-tailed data (FT). The time series data contains symmetric and asymmetric outliers that can affect forecasting. The forecasting method used for the trend data pattern is the Holt smoothing method. The forecasting of the data series when it is spinning using the Holt smoothing method is not good enough so that it requires a handler with the smoothing method of Holt robustness. The Holt robustness smoothing method that is carried out on time series simulation data is better used for the condition of scattered data compared to the Holt smoothing method. This is indicated by the value of evaluating the goodness of the method, namely the value of MAD (Mean Absolute Deviation) produced. The smaller MAD value for CD condition training data is the Holt smoothing method, while the data testing method for Holt and robust Holt smoothing is almost comparable. SO's condition for training data and data testing for smaller MAD values is the smoothing method of robust Holt. The condition of AO for training data and data testing for smaller MAD values is the smoothing method of robust Holt. In addition, the MAD value in FT conditions for training data and data testing found almost comparable results between the two methods.

Sign in / Sign up

Export Citation Format

Share Document