A Parameter Based Customized Artificial Neural Network Model for Crop Yield Prediction

Shastry, K. Aditya; Sanjay, H. A.; Deshmukh, Abhijeeth

doi:10.3923/jai.2016.23.32

Cited by 20 publications

(12 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A parameter-based customized Artificial Neural Network (ANN) [9] model was proposed for wheat yield prediction. ANN and Multiple Linear Regression (MLR) were used in this model.…”

Section: Saranya S Sathappanmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Model Ensemble Depth Adaptive Deep Neural Network for Crop Yield Prediction

Saranaya*,

Sathappan

2020

IJRTE

View full text Add to dashboard Cite

Accurate prediction of crop yield enables critical tasks such as identifying the optimum crop profile for planting, assigning government resources and decision-making on imports and exports in more commercialized systems. In past few years, Machine Learning (ML) techniques have been widely used for crop yield prediction. Deep Neural Network (DNN) was introduced for crop yield. The crop yield prediction accuracy based on DNN was further improved by Multi-Model DNN (MME-DNN). It predicted the crop yield by modeling climatic, weather and soil parameters through statistical model and DNN. The MME-DNN is not scalable when new data appears consecutively in a stream form. In order to solve this problem, an Online Learning (OL) is introduced for crop yield prediction. In OL, DNN is learned in an online setting which optimizes the objective function regarding shallow model. But, a fixed depth of the network is used in ODL and it cannot be changed during the training process. So, Multi-Model Ensemble Depth Adaptive Deep Neural Network (MME-DADNN) is proposed in this paper to adaptively decide the depth of the network for crop yield prediction. A training scheme for OL is designed through a hedge back propagation. It automatically decides the depth of the DNN using Online Gradient Descent (OGD) in an online manner. Also, a smoothing parameter is introduced in OL to set a minimum weight for every depth of DNN and it also contributes a balance between exploitation and exploration. The crop yield is predicted from the soil, weather and climate parameters and their variation over four years by applying the MME-DADNN. Thus, by adaptively changing the depth of the DNN the performance of crop yield prediction is enhanced.

show abstract

“…A parameter-based customized Artificial Neural Network (ANN) [9] model was proposed for wheat yield prediction. ANN and Multiple Linear Regression (MLR) were used in this model.…”

Section: Saranya S Sathappanmentioning

confidence: 99%

“…It is done when the ground truth is revealed. The weight updation is given as follows, (9) In (9), the discount rate parameter is represented as which is ranges from 0 to 1. Hence, a classifier's weight is cut-rated by a factor of in every iteration.…”

Section: Multi-model Ensemble-depth Adaptive Deep Neural Networkmentioning

confidence: 99%

Multi-Model Ensemble Depth Adaptive Deep Neural Network for Crop Yield Prediction

Saranaya*,

Sathappan

2020

IJRTE

View full text Add to dashboard Cite

show abstract

“…In this study wheat yield was predicted by considering its different parameters. Better wheat yield was predicted by using C-ANN model (Aditya Shastry et al, 2016).…”

Section: Figure 1 the Crop Yield Of Winter Wheat On The Different Numentioning

confidence: 99%

The Impact of Nutrition Optimization on Crop Yield of Winter Wheat Varieties (Triticum Aestivum L.) and Modeling of Regularities of Its Dependence on Structure Indicators

Panfilova¹,

Mohylnytska²

2019

AgricultForest

View full text Add to dashboard Cite

The article presents the results of studies conducted in 2011-2016 years on the southern chernozem in the southern Steppe of Ukraine, studied the efficiency of processing winter wheat crops modern growth-regulating drugs in the main periods of vegetation of the crop on the background of mineral fertilizers application. It was determined that the introduction of pre-sowing cultivation of winter wheat fertilizer in a dose of N 30 P 30 (background) and the use of foliar fertilizing of crops at the beginning of the resumption of spring vegetation and the beginning of stooling complex organic fertilizers Organic D2 and Escort-bio created favorable conditions for the formation of optimal indicators of the structure of the crop and, accordingly, a high level of grain yield of the studied varieties. In the variants of fertilizer Organic D2 and Escort-bio plants of winter wheat variety Kolchuga formed 4,42-4,48 t / ha of grain, and plants of Zamozhnist formed 4,96-4,99 t/ha, which exceeded the control by 52,9-55,0 and 62,6-63,6%, respectively. From the studied varieties of winter wheat on a set of indicators, it was determined Zamozhnist as the best variety.

show abstract

“…Figure5. Customized Artificial Neural Networks (C-ANN) model for wheat yield prediction (Shastry et al 2016) [55] C.…”

Section: Bmentioning

confidence: 99%

“…Shastry et al (2016) [55] contrasted two recognized prediction systems to expect wheat yield which are artificial neural Networks (ANN) and Multiple Linear Regression (MLR). The researchers considered a several parameters like precipitation amount, crop biomass, soil evaporation, transpiration, extractable soil water (ESW) and fertilizer added (NO3).…”

mentioning

confidence: 99%

Untitled

2018

International Journal of Innovative Research in Electrical, Ele

View full text Add to dashboard Cite

Manual identification, classification and taxonomy of a definite and specific species or plant disease are generally obstructed by several difficulties such as time consumption, the limited number of expert specialists and the increase in the number of the defined characteristics of each species. The steady progress of the computational technology over the last few years concerning the automated species recognition including plant structures is be easier particularly in the presence of huge databases of information and the enhancement of classification and analyzing image technology. Several investigators are currently working in agriculture field mainly those concerned with plant identification or of plant disease recognition through image processing, extraction of identical features and classifying them into exact classes. In this review, the integration of computer science with agriculture has been discussed to detect, quantify, predict, early identify and classify plant diseases as well as forecasting agricultural crops using different machine learning techniques. Weather forecasting, smart irrigation system, plant leaf identification, etc will also discussed. The aim of this paper is to provide the investigators particularly biologists with computational recognition techniques as well as the possibility of using image informative morphological features of a species or a group of related species in recognition of many biological organisms including plants and microorganisms.

show abstract

A Parameter Based Customized Artificial Neural Network Model for Crop Yield Prediction

Cited by 20 publications

References 1 publication

Multi-Model Ensemble Depth Adaptive Deep Neural Network for Crop Yield Prediction

Multi-Model Ensemble Depth Adaptive Deep Neural Network for Crop Yield Prediction

The Impact of Nutrition Optimization on Crop Yield of Winter Wheat Varieties (Triticum Aestivum L.) and Modeling of Regularities of Its Dependence on Structure Indicators

Untitled

Contact Info

Product

Resources

About