Conference Paper

Sorghum Yield Prediction using Machine Learning

To read the full-text of this research, you can request a copy directly from the authors.


Estimation of a future agricultural production is an important challenge for farmers. In this paper, we propose a system based on machine learning algorithms to estimate farm yields. The experiments were conducted on a Sorghum field. We use TensorFlow with Convolutional Neural Networks and Linear Regression. These algorithms allow us 1) to detect the different ears of Sorghum on an image and 2) to estimate their weight.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... The yield prediction can be defined from the earlier dataset and what type of latest technologies available and applicable on all the ways based on the current crop, climatic and financial situations for improving the yield. A study [28] used Tensor Flow with Convolutional Neural Networks and Linear Regression for estimating the yield from Sorghum field. ...
Machine learning is a promising domain which is widely used now a days in the field of agriculture. The availability of manpower for agriculture is not enough and skill full farmers are less. Understanding the situation of the crop is not that much easy to detect and prevent the diseases in the crop. It is also widely employed in various agricultural fields such as topsoil management, yield management, water management, disease management and climate conditions. The machine learning models facilitate very fast and optimal decisions. The model of machine learning involves with training and testing to predict the accuracy of the result. The use of machine learning in agriculture helps to increase the productivity and better management on soil classification, disease detection, species management, water management, yield prediction, crop quality and weed detection. This article aims at providing detailed information on various machine learning approaches proposed in the past five years by emphasizing the advantage and disadvantages. It also compares different machine learning algorithms used in the modern agricultural field.
In India, agribusiness-related ventures are the significant wellspring of living for the individuals. It is one of the nations which experience the ill effects of characteristic disasters like dry season or flood which harms the harvest. This prompts tremendous money-related misfortune for the nation. Individuals of India have been rehearsing farming for quite a long time, yet the outcomes are failing to satisfy because of different variables that influence the harvest yield. Predicting the crop yield in advance requires an efficient investigation of gigantic information originating from different factors like soil quality, pH, N, P, K and so on for storing, selling, pricing and imports exports, etc. Through data mining, insights can be drawn by analyzing the huge volume of data and draw very important and conclusions for any year yield. The prediction of any crop yield majorly depends on accuracy of the extracted features and how appropriately classifiers have been employed.
Full-text available
Deep learning has become an area of interest to the researchers in the past few years. Convolutional Neural Network (CNN) is a deep learning approach that is widely used for solving complex problems. It overcomes the limitations of traditional machine learning approaches. The motivation of this study is to provide the knowledge and understanding about various aspects of CNN. This study provides the conceptual understanding of CNN along with its three most common architectures, and learning algorithms. This study will help researchers to have a broad comprehension of CNN and motivate them to venture in this field. This study will be a resource and quick reference for those who are interested in this field.
Full-text available
Existing crop models produce unsatisfactory simulation results and are operationally complicated.Thepresent study, however, demonstrated the unique advantages of statisticalcrop models for large-scale simulation. Using rice as the research crop, a supportvectormachine-based open crop model (SBOCM) was developed by integrating developmental stage and yield prediction models.Basic geographical information obtained by surface weather observation stations in China and the 1:1000000 soil database published by the Chinese Academy of Sciences were used. Based on the principle of scale compatibility of modeling data, an open reading frame was designed for the dynamic daily input of meteorological data and output of rice development and yield records. This was used to generate rice developmental stage and yield prediction models, which were integrated into the SBOCM system. The parameters, methods, error resources, and other factors were analyzed. Although not a crop physiology simulation model,the proposed SBOCM can be used for perennial simulation and one-year rice predictionswithin certain scale ranges. It is convenient for data acquisition, regionally applicable, parametrically simple, and effective for multi-scale factor integration. It has the potential for future integration with extensive social and economic factors to improve the prediction accuracy and practicability.
Full-text available
With the rise and development of information technology (IT) services, the amount of data generated is rapidly increasing. Data from many different places are inconsistent. Data capture, storage and analysis have major challenges. Most data analysis methods are unable to handle such large amounts of data. Many studies employ neural networks, mostly specifying the number of hidden layers and neurons according to experience or formula. Different sets of network topologies have different results, and the best network model is selected. This investigation proposes a system based on the ensemble neural network (ENN). It creates multiple network models, each with different numbers of hidden layers and neurons. A model that does not achieve the accuracy rate is discarded. The proposed system derives the weighted average of all remaining network models to improve the accuracy of the prediction. This study applies the proposed method to generate agricultural yield predictions. The agricultural production process in Taiwan is more complex than those of manufacturing or other industries. The Council of Agriculture provides agricultural forecasting primarily based on the planted area and experience to predict the yield, but without consideration of the overall planting environment. This work applies the proposed data analysis method to agriculture. The method based on ENN has a much lower error rate than traditional back-propagation neural networks, while multiple regression analysis has an error rate of 12.4%. Experimental results reveal that the ENN method is better than traditional back-propagation neural networks and multiple regression analysis.
In this article, a non-destructive method is proposed to count the number of fruits on a coffee branch by using information from digital images of a single side of the branch and its growing fruits. In order to do this, 1018 coffee branches at different ripening stages. They had different numbers of fruits, harvest dates, were of different varieties, and were at different stages of coffee tree?s life. A Machine Vision System (MVS) was constructed, which was capable of counting and identifying harvestable and not harvestable fruits in a set of images corresponding to a specific coffee branch was constructed. This MVS consists of an image acquisition system, based on mobile devices (it does not require to control of the environmental conditions), and an image processing algorithm to classify and detect each one of the fruits in the acquired images. After obtaining information regarding the number of fruits identified by the MVS, linear estimation models were constructed between the detected fruits automatically and the ones observed on the coffee branch. These models were calculated for fruits in three categories: harvestable, not harvestable, and fruits whose maturation stage were disregarded. These models link the fruits that are counted automatically to the ones actually observed with an higher than 0.93 one-to-one. Not only is the MVS used to estimate the number of fruits on the branch but also to estimate their maturation percentage and weight. The MVS was validated in four Variedad Castillo? coffee plots, in different stages of development and with different densities. We found that MVS neither overestimates nor underestimates the number of fruits and that it shows a correlation higher than 0.90 at early stages of crop development, when tree fruits are still not harvestable. The information obtained in this research will spawn a new generation of tools for coffee growers to use. It is an efficient, non-destructive, and low-cost method which offers useful information for them to plan agricultural work and obtain economic benefits from the correct administration of resources.
Understanding yield limiting factors requires high resolution multi-layer information about factors affecting crop growth and yield. Therefore, on-line proximal soil sensing for estimation of soil properties is required, due to the ability of these sensors to collect high resolution data (>1500 sample per ha), and subsequently reducing labor and time cost of soil sampling and analysis. The aim of this paper is to predict within field variation in wheat yield, based on on-line multi-layer soil data, and satellite imagery crop growth characteristics. Supervised self-organizing maps capable of handling existent information from different soil and crop sensors by utilizing an unsupervised learning algorithm were used. The performance of counter-propagation artificial neural networks (CP-ANNs), XY-fused Networks (XY-Fs) and Supervised Kohonen Networks (SKNs) for predicting wheat yield in a 22 ha field in Bedfordshire, UK were compared for a single cropping season. The self organizing models consisted of input nodes corresponded to feature vectors formed from normalized values of on-line predicted soil parameters and the satellite normalized difference vegetation index (NDVI). The output nodes consisted of yield isofrequency classes, which were predicted from the three trained networks. Results showed that cross validation based yield prediction of the SKN model for the low yield class exceeded 91% which can be considered as highly accurate given the complex relationship between limiting factors and the yield. The medium and high yield class reached 70% and 83% respectively. The average overall accuracy for SKN was 81.65%, for CP-ANN 78.3% and for XY-F 80.92%, showing that the SKN model had the best overall performance.
Guide pour la production et l'utilisation des cartes de rendement
  • Stéphane Martel
  • Charles Fournier-Marcotte
  • Hélène Moore
Stéphane Martel, Charles Fournier-Marcotte and Hélène Moore, "Guide pour la production et l'utilisation des cartes de rendement," 2015.
Sorghum" The Editors of Encyclopaedia Britannica
  • Melissa Petruzzello
Melissa Petruzzello, "Sorghum" The Editors of Encyclopaedia Britannica, 2016.
Guide pour l'évaluation du rendemant et l'estimation de la production horticloe
  • Paden
PADEN, "Guide pour l'évaluation du rendemant et l'estimation de la production horticloe," Unit de Coordination du Programme (UCP) , 2014.
  • Tom M Mitchell
Tom M. Mitchell, "Machine Learning", McGraw Hill, 2018.