Carrot Yield Mapping: A Precision Agriculture Approach Based on Machine Learning

Wei, Marcelo Chan Fu; Maldaner, Leonardo Felipe; Ottoni, Pedro Medeiros Netto; Molin, José Paulo

doi:10.3390/ai1020015

Cited by 47 publications

(31 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the test dataset, the RF regression had RMSE values ranging from 4.63 to 5.47 Mg ha −1 , which was lower than the MLR model (RMSE closer to 6.0 Mg ha −1 ). Other studies reported RF prediction as more accurate than MLR [2,53].…”

Section: Selection Of Predictor Variablesmentioning

confidence: 97%

Sugarcane Yield Mapping Using High-Resolution Imagery Data and Machine Learning Technique

et al. 2021

Self Cite

View full text Add to dashboard Cite

Yield maps provide essential information to guide precision agriculture (PA) practices. Yet, on-board yield monitoring for sugarcane can be challenging. At the same time, orbital images have been widely used for indirect crop yield estimation for many crops like wheat, corn, and rice, but not for sugarcane. Due to this, the objective of this study is to explore the potential of multi-temporal imagery data as an alternative for sugarcane yield mapping. The study was based on developing predictive sugarcane yield models integrating time-series orbital imaging and a machine learning technique. A commercial sugarcane site was selected, and Sentinel-2 images were acquired from the beginning of the ratoon sprouting until harvesting of two consecutive cropping seasons. The predictive yield models RF (Random forest) and MLR (Multiple Linear Regression) were developed using orbital images and yield maps generated by a commercial sensor-system on harvesting. Original yield data were filtered and interpolated with the same spatial resolution of the orbital images. The entire dataset was divided into training and testing datasets. Spectral bands, especially the near-infrared at tillering crop stage showed greater contribution to predicting sugarcane yield than the use of derived spectral vegetation indices. The Root Mean Squared Error (RMSE) obtained for the RF regression based on multiple spectral bands was 4.63 Mg ha−1 with an R2 of 0.70 for the testing dataset. Overall, the RF regression had better performance than the MLR to predict sugarcane yield.

show abstract

Section: Selection Of Predictor Variablesmentioning

confidence: 97%

Sugarcane Yield Mapping Using High-Resolution Imagery Data and Machine Learning Technique

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, Taghizadeh-Mehrjardi et al [51] created a method to assess the suitability of land for two main crops (i.e., wheat and rainfed barley) according to the Organization's "Land Suitability Assessment Framework" for Agriculture and Food (FAO). Wei et al [52] developed a method to generate a carrot yield map applying a random forest regression algorithm on a database composed of satellite spectral data and ground carrot yield sampling. Mosavi et al [53] propose a method that includes new ML models for the susceptibility mapping of soil water erosion.…”

Section: Answer For Rq4: What Is the Area Of Agriculture In Which Big Data Machine Learning Is Used?mentioning

confidence: 99%

Use and Adaptations of Machine Learning in Big Data—Applications in Real Cases in Agriculture

Cravero

Sepúlveda

2021

Electronics

View full text Add to dashboard Cite

The data generated in modern agricultural operations are provided by diverse elements, which allow a better understanding of the dynamic conditions of the crop, soil and climate, which indicates that these processes will be increasingly data-driven. Big Data and Machine Learning (ML) have emerged as high-performance computing technologies to create new opportunities to unravel, quantify and understand agricultural processes through data. However, there are many challenges to achieve the integration of these technologies. It implies making some adaptations to ML for using it with Big Data. These adaptations must consider the increasing volume of data, its variety and the transmission speed issues. This paper provides information on the use of Big Data and ML for agriculture, identifying challenges, adaptations and the design of architectures for these systems. We conducted a Systematic Literature Review (SLR), which allowed us to analyze 34 real cases applied in agriculture. This review may be of interest to computer or data scientists and electronic or software engineers. The results show that manipulating large volumes of data is no longer a challenge due to Cloud technologies. There are still challenges regarding (1) processing speed due to little control of the data in its different stages, raw, semi-processed and processed data (value data); (2) information visualization systems, which support technical data little understood by farmers.

show abstract

“…As observed in other studies, Bayesian networks can investigate appropriate and interpretable framework for the simultaneous modeling of multiple quantitative traits in better predictive power result in the context of additive genetic models [35] Among the other studies that had good performance for example [36] used VW-4DEnSRF algorithm to study the area and winter wheat yield estimation based on the WOFOST crop model and a crop yield assimilation system. Wei, et al [25], study highlighted that despite of the impact machine learning approaches in understanding and exploiting GEI for prediction, there is still some room for expanding and improving their use in applications not yet explored. [37] used the deep learning model such as convolutional neural network (CNN) and artificial neural network (ANN) to Self-Predictable Crop Yield Platform (SCYP) based on crop diseases using deep learning that collects weather information (temperature, humidity, sunshine, precipitation, etc.)…”

Section: Multi Target Performancementioning

confidence: 99%

Application of Bayesian Networks of Genotype by Environment Interaction Evaluation Under Plant Disease, Soil Types and Climate Condition-using Bayesia Lab

Omer¹

2021

AJAMS

View full text Add to dashboard Cite

Genotype by environment interaction (GEI) linked to plant disease, soil properties and climate conditions add potential value for a breeding program to underpin decision making. In understanding genotype x environment interaction, the most challenging factors are the identification of genetic variation for a range of traits and their responsiveness to the climate change factors. In order to study the complex relationships with genetic and non-genetic factors, the application of Bayesian network tools will help understand and accelerate plant breeding progress and improve the efficiency of crop production. In this study, we proposed the application of Bayesian networks (BNs) to evaluate genotype by environment interaction under plant diseases, soil type, and climate variables. An adapted to simulate multiple environmental trial (MET) data of maize (corn) was used to examine the performance of the BN predictive modeling using BayesiaLab for deriving knowledge and graphical structure for exploring GEI diagnosis and analysis. The results highlighted that genotypes have the same probability and the frequentist of rainfall, temperature, soil type, and disease type occurred as <=88 (46%), 35 (37%), clay (27%), and MB (47%) respectively, which have to monitor reflects in each discretization. This study provided a roadmap to knowledge modeling of GEI using BayesiaLab software. On a broader scale, this study helps predict the yield of crop varieties by understanding agronomic and environmental factors under farm conditions rather than conducting long-term agricultural testing under well-controlled conditions of the on-station trials. Future improvements of BNs application of METs should consider working on a larger and more detailed soil and irrigation system linked to agro system.

show abstract

Carrot Yield Mapping: A Precision Agriculture Approach Based on Machine Learning

Cited by 47 publications

References 55 publications

Sugarcane Yield Mapping Using High-Resolution Imagery Data and Machine Learning Technique

Sugarcane Yield Mapping Using High-Resolution Imagery Data and Machine Learning Technique

Use and Adaptations of Machine Learning in Big Data—Applications in Real Cases in Agriculture

Application of Bayesian Networks of Genotype by Environment Interaction Evaluation Under Plant Disease, Soil Types and Climate Condition-using Bayesia Lab

Contact Info

Product

Resources

About