Improved weather indices based Bayesian regression model  for forecasting crop yield

As agriculture is the backbone of the Indian economy, Government needs a reliable forecast of crop yield for planning new schemes. The most extensively used technique for forecasting crop yield is regression analysis. The significance of parameters is one of the major problems of regression analysis. Non-significant parameters lead to absurd forecast values and these forecast values are not reliable. In such cases, models need to be improved. To improve the models, we have incorporated prior knowledge through the Bayesian technique and investigate the superiority of these models under the Bayesian framework. The Bayesian technique is one of the most powerful methodologies in the modern era of statistics. We have discussed different types of prior (informative, non-informative and conjugate priors). The Markov chain Monte Carlo (MCMC) methodology has been briefly discussed for the estimation of parameters under Bayesian framework. To illustrate these models, production data of banana, mango and wheat yield data are taken under consideration. We compared the traditional regression model with the Bayesian regression model and conclusively infer that the models estimated under Bayesian framework provided superior results as compared to the models estimated under the classical approach.

Download Full-text

Simulation Study for Penalized Bayesian Elastic Net Quantile Regression

Al-Qadisiyah Journal Of Pure Science ◽

10.29350/qjps.2021.26.3.1306 ◽

2021 ◽

Vol 26 (3) ◽

Author(s):

Muntadher Almusaedi ◽

Ahmad Naeem Flaih

Keyword(s):

Regression Analysis ◽

Quantile Regression ◽

Regression Model ◽

Prior Distribution ◽

Main Idea ◽

Bayesian Regression ◽

Elastic Net ◽

Adaptive Lasso ◽

Quantile Regression Model ◽

Truncated Gamma Distribution

Bayesian regression analysis has great importance in recent years, especially in the Regularization method, Such as ridge, Lasso, adaptive lasso, elastic net methods, where choosing the prior distribution of the interested parameter is the main idea in the Bayesian regression analysis. By penalizing the Bayesian regression model, the variance of the estimators are reduced notable and the bias is getting smaller. The tradeoff between the bias and variance of the penalized Bayesian regression estimator consequently produce more interpretable model with more prediction accuracy. In this paper, we proposed new hierarchical model for the Bayesian quantile regression by employing the scale mixture of normals mixing with truncated gamma distribution that stated by (Li and Lin, 2010) as Laplace prior distribution. Therefore, new Gibbs sampling algorithms are introduced. A comparison has made with classical quantile regression model and with lasso quantile regression model by conducting simulations studies. Our model is comparable and gives better results.

Download Full-text

Wheat yield as influenced by urea applied with nitrification inhibitor and gibberellic acid

10.5194/egusphere-egu2020-4842 ◽

2020 ◽

Author(s):

Rayehe Mirkhani ◽

Mehdi Shorafa ◽

Mohammad Zaman

Keyword(s):

Grain Yield ◽

Crop Yield ◽

Stem Elongation ◽

Block Design ◽

Wheat Yield ◽

Nitrification Inhibitor ◽

Growth And Yield ◽

Control Treatment ◽

Yield Data ◽

Economic Implications

Among the essential plant nutrients, nitrogen (N) is the most needed. Farmer apply N fertilizer, predominantly urea to meet crop N demand. However, a greater proportion of the applied urea-N is not being used by plants and lost to the atmosphere as ammonia or greenhouse gases. Therefore, it is necessary to enhance N use efficiency (NUE) of applied urea by minimizing such losses, which has environmental and economic implications. Nitrification inhibitor, such as nitrapyrin (NP), has the most potential to minimise N losses and enhance crop yield. Similarly, plant hormones, such as GA3, has the potential to reduce abiotic stress and improve plant growth and yield. &#160;&#160; A field experiment was established on an arable site at University of Tehran, Karaj to determine the effect of urea applied with Nitrapyrin and GA3 on wheat yield in 2018-2019. Karaj has a Mediterranean climate with annual precipitation of 265 mm. A randomized complete block design in five replications was used in this study. Treatments were: T1 (control treatment - without urea), T2 (farmers practice - 138 kg N/ha), and T3 (best practice - 138 kg N/ha+NP+GA3). Urea was applied in three split applications (46 kg N/ha) at growth stage (GS 21) or tillering, (GS 32) or stem elongation, and (GS 40) or booting. GA3 in T3 treatment, was applied only at stem elongation stage.&#160; The crop yield data showed that, urea applied with NP and GA3 had a significant (p &#8804; 0.01) effect on grain yield, biological yield, number of grains, 1000-grain weight and % Harvest Index (%HI) compared to other treatments. Urea applied with NP and GA3 increased grain yield (10.30 t ha-1) by 13.9% and 46.1% compared to farmer practices (9.04 t ha-1) and control treatment (7.05 t ha-1). These results suggest that co-application of urea with NP and GA3 has the potential to enhance wheat yield in semi-arid area of Iran.

Download Full-text

May spring seasonal forecasts improve a climate service providing cereal yield predictions?

10.5194/ems2021-76 ◽

2021 ◽

Author(s):

Maria Nieves Garrido ◽

J. Ignacio Villarino ◽

Eroteida Sánchez ◽

Inmaculada Abia ◽

Marta Dominguez ◽

...

Keyword(s):

Crop Yield ◽

Growth Model ◽

Wheat Yield ◽

Crop Growth ◽

Seasonal Forecasts ◽

Crop Growth Model ◽

Yield Data ◽

Winter Climate ◽

Winter Cereal ◽

Climate Service

Following the need of winter cereal farmers from the main producing region (Castilla y Le&#243;n) in Spain to estimate crop yield with at least one season of anticipation, we have developed a climate service based essentially on current and historical meteorological observations, on spring seasonal forecasts from ECMWF System 5 and on the crop growth model AquaCrop. Different experiments have been designed to produce both a synthetic yield database serving as observed truth and three different seasonal forecasting strategies. Calculation of objective verification scores for deterministic and probabilistic crop yield forecasts -including an assessment of their potential economic value- in hindcast mode determines the quality of this service and the differences among forecasting strategies. We demonstrate that the three compared strategies show good skill of wheat yield forecasts at the beginning of July, although the meteorological forcing for Aquacrop simulations between 1st April and 30th June is very different for the three compared strategies. The important role of the memory from previous (autumn and winter) climate conditions carried by the crop growth model is analysed and discussed.&#160; A yearly assessment also allows some preliminary estimation of the value and possible benefits of the service for final users. Finally, we conclude that the simulation synthetically producing the observed truth compares rather well &#8211;especially the interannual variability- with other yield data based on surveys and experts estimations although it overestimates yield.&#160;Users have played a decisive role in co-design and co-development phases of this climate service. They have also actively intervened in the analysis and evaluation of results.&#160;

Download Full-text

A New Hyperprior Distribution for Bayesian Regression Model with Application in Genomics

10.1101/102244 ◽

2017 ◽

Author(s):

Renato Rodrigues Silva

Keyword(s):

Regression Analysis ◽

Regression Model ◽

Regression Coefficient ◽

R Package ◽

Bayesian Regression ◽

Predictor Variables ◽

Chi Square ◽

Wide Context ◽

Genome Wide ◽

Large P Small N

AbstractIn the regression analysis, there are situations where the model have more predictor variables than observations of dependent variable, resulting in the problem known as “large p small n”. In the last fifteen years, this problem has been received a lot of attention, specially in the genome-wide context. Here we purposed the bayes H model, a bayesian regression model using mixture of two scaled inverse chi square as hyperprior distribution of variance for each regression coefficient. This model is implemented in the R package BayesH.

Download Full-text

Mining effect of Temperature and Rainfall to develop an Empirical Model for Wheat Yield Prediction

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813666200129105708 ◽

2020 ◽

Vol 13 ◽

Author(s):

Kanwal Preet Singh Attwal ◽

Amardeep Singh Dhiman

Keyword(s):

Crop Yield ◽

Meteorological Factors ◽

Wheat Yield ◽

Effect Of Temperature ◽

Yield Prediction ◽

Total Rainfall ◽

Yield Data ◽

Average Temperature ◽

Whole Wheat ◽

Maximum Variance

Background: Crop yield is affected by several agronomic factors such as soil type and date of sowing, and meteorological factors such as temperature and rainfall. While the agronomic factors are responsible for inter-region variations in yield, the year-wise yield variation in a particular region may be attributed to meteorological factors. Various Data Mining Techniques can be applied to analyse the effect of these factors on crop yield. Objective: To develop a model for prediction of Block-wise average wheat yield in Patiala district of Punjab, India. Method: Sampling is used for the collection of the yield data, and the data concerning temperature and rainfall is obtained from Indian Meteorological Department, Pune. The data is then pre-processed and analysed to study the effect of phase-wise average temperature and total rainfall on the wheat yield. The factors that are found to significantly affect yield are used for building a model for yield prediction. Results: It is found that the average temperature and the total rainfall for the whole wheat growing season are not much of help in explaining the variations in yearly wheat yield. The temperature and rainfall have different effects at different stages of plant growth and the yield is affected accordingly. It is inferred that that the average temperature and the total rainfall during the vegetative phase, and the grain development and ripening phase are the most important parameters for prediction of wheat yield. Conclusion: Stepwise selection mechanism is used to choose the variables whose inclusion explains the maximum variance in yield. The model is evaluated based on different parameters and is found to explain 95.6% of the yearly variations in yield.

Download Full-text

The Use of Crop Yield Autocorrelation Data as a Sustainable Approach to Adjust Agronomic Inputs

Sustainability ◽

10.3390/su13042362 ◽

2021 ◽

Vol 13 (4) ◽

pp. 2362

Author(s):

Thomas M. Koutsos ◽

Georgios C. Menexes ◽

Andreas P. Mamolos

Keyword(s):

Decision Making ◽

Spatial Analysis ◽

Crop Yield ◽

Spatial Autocorrelation Analysis ◽

Autocorrelation Analysis ◽

Yield Data ◽

Site Specific ◽

Production Areas ◽

Short Time ◽

Monitor Data

Agricultural fields have natural within-field soil variations that can be extensive, are usually contiguous, and are not always traceable. As a result, in many cases, site-specific attention is required to adjust inputs and optimize crop performance. Researchers, such as agronomists, agricultural engineers, or economists and other scientists, have shown increased interest in performing yield monitor data analysis to improve farmers’ decision-making concerning the better management of the agronomic inputs in the fields, while following a much more sustainable approach. In this case, spatial analysis of crop yield data with the form of spatial autocorrelation analysis can be used as a practical sustainable approach to locate statistically significant low-production areas. The resulted insights can be used as prescription maps on the tractors to reduce overall inputs and farming costs. This aim of this work is to present the benefits of conducting spatial analysis of yield crop data as a sustainable approach. Current work proves that the implementation of this process is costless, easy to perform and provides a better understanding of the current agronomic needs for better decision-making within a short time, adopting a sustainable approach.

Download Full-text

Gridded 1 km × 1 km emission inventory for paddy stubble burning emissions over north-west India constrained by measured emission factors of 77 VOCs and district-wise crop yield data

The Science of The Total Environment ◽

10.1016/j.scitotenv.2021.148064 ◽

2021 ◽

pp. 148064

Author(s):

Ashish Kumar ◽

Haseeb Hakkim ◽

Baerbel Sinha ◽

Vinayak Sinha

Keyword(s):

Crop Yield ◽

Emission Inventory ◽

Emission Factors ◽

Yield Data ◽

North West ◽

Stubble Burning

Download Full-text

Modeling of Durum Wheat Yield Based on Sentinel-2 Imagery

Agronomy ◽

10.3390/agronomy11081486 ◽

2021 ◽

Vol 11 (8) ◽

pp. 1486

Author(s):

Chris Cavalaris ◽

Sofia Megoudi ◽

Maria Maxouri ◽

Konstantinos Anatolitis ◽

Marios Sifakis ◽

...

Keyword(s):

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Vegetation Indices ◽

Model Development ◽

Wheat Yield ◽

Growth Period ◽

Yield Data ◽

Water Index ◽

Normalized Difference Water Index ◽

Sentinel 2

In this study, a modelling approach for the estimation/prediction of wheat yield based on Sentinel-2 data is presented. Model development was accomplished through a two-step process: firstly, the capacity of Sentinel-2 vegetation indices (VIs) to follow plant ecophysiological parameters was established through measurements in a pilot field and secondly, the results of the first step were extended/evaluated in 31 fields, during two growing periods, to increase the applicability range and robustness of the models. Modelling results were examined against yield data collected by a combine harvester equipped with a yield-monitoring system. Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) were examined as plant signals and combined with Normalized Difference Water Index (NDWI) and/or Normalized Multiband Drought Index (NMDI) during the growth period or before sowing, as water and soil signals, respectively. The best performing model involved the EVI integral for the 20 April–31 May period as a plant signal and NMDI on 29 April and before sowing as water and soil signals, respectively (R2 = 0.629, RMSE = 538). However, model versions with a single date and maximum seasonal VIs values as a plant signal, performed almost equally well. Since the maximum seasonal VIs values occurred during the last ten days of April, these model versions are suitable for yield prediction.

Download Full-text