Random Forests for Global and Regional Crop Yield Predictions

Jeong, Jig Han; Resop, Jonathan P.; Mueller, Nathaniel D.; Fleisher, David H.; Yun, Kyungdahm; Butler, Ethan E.; Timlin, Dennis; Shim, Kyo Moon; Gerber, James; Reddy, Vangimalla R.; Kim, Sung Hyun

doi:10.1371/journal.pone.0156571

Cited by 513 publications

(289 citation statements)

References 41 publications

Supporting

Mentioning

224

Contrasting

Unclassified

Order By: Relevance

“…Figure 6 illustrates the average accuracy, sensitivity and specificity value of proposed method, which is superior compared to existing approaches. Averagely, the accuracy gap between the proposed and existing methods are 23.04%, 20.093%, 13.09%, 7.02% and 14.34% reduction in accuracy value associated to SOM-DNN, SOM-KNN, weighted-SOM-KNN, RF-MLR [17], and SOM-LVQ [18]. Similarly, the proposed method delivers better performance compared to the existing approaches in terms of sensitivity and specificity.…”

Section: Results Of Classification Evaluationmentioning

confidence: 86%

“…Similarly, the 70% training and 30% testing of collected data delivers, 0.8319 of precision and 0.9 of recall. The graphical representation of precision and recall comparison is stated in the [17] evaluated a machine-learning method: RF for predicting crop yield responses to climate and biophysical variables at global and regional scales in wheat, maize, and potato in comparison with MLR serving as a benchmark. RF was found highly capable of predicting crop yields and outperformed MLR benchmarks in all performance statistics that were compared.…”

Section: Results Of Classification Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Based Weighted SOM to Forecast Weather and Crop Prediction for Agriculture Application

Mohan¹,

Patil²

2018

IJIES

View full text Add to dashboard Cite

Abstract:One of the most experimentally difficult problem in the world is weather forecasting, which is a basic mechanism in meteorology. Especially in data mining system, there are different information mining strategies are available, for example, K-Means, Artificial Neural Network (ANN) and Support Vector Machine (SVM), etc. These weather predicting strategies are financially high and also very inconsistent for large datasets. To overcome these issues, an effective dimensionality reducing strategy: Self Organizing Map (SOM) is proposed along with Latent Dirichlet Allocation (LDA). The SOM strategy is one of the proper dimensionality reducing strategy to highlight the self-arranging outline. After reducing the measurement, the dimensionality reduced information are used to forecast climate for a reasonable outcome. A reasonable season for an appropriate crop is arranged with the guide of Deep Neural Network (DNN) classification system. This research work depends on finding appropriate information model, which helps in accomplishing high precision and simplification for value forecast. Finally, the experimental outcome shows that the proposed approach improved accuracy in weather and crop prediction up to 7-23% compared to the existing methods.

show abstract

Section: Results Of Classification Evaluationmentioning

confidence: 86%

Section: Results Of Classification Evaluationmentioning

confidence: 99%

Deep Learning Based Weighted SOM to Forecast Weather and Crop Prediction for Agriculture Application

Mohan¹,

Patil²

2018

IJIES

View full text Add to dashboard Cite

show abstract

“…The calibration performance of RF models was shown in Figure 3. Compared with previous model calibration at county scale [7,11,41], the model calibration in this study was based on pixel scale, which could improve the performance of crop yield estimation model at finer resolution. No matter for maize or sunflower, the R 2 and adjusted R 2 of all RF models were between 0.80 and 0.90, and the difference between R 2 and adjusted R 2 was very small due to the number of calibration data (272 for maize and 432 for sunflower) was far more than the number of predictors, which indicated that there was no over fitting phenomenon in our calibrated models.…”

Section: Resultsmentioning

confidence: 99%

“…In this study, we used RF regression function implemented in the “Random Forest” package within Matlab R2017b software developed by MathWorks (Natick, MA, USA) to estimate the crop yield. Using remote sensing data as inputs, RF regression algorithm has been successfully applied to crop yield estimation in recent years [7,41,42]. …”

Section: Methodsmentioning

confidence: 99%

“…The ANN has been successfully applied to yield estimation of various crops, such as maize [11], wheat [37], potato [38], melon [39] and grassland dry matter yield [40]. The RF method has also been used in crop yield estimation, especially for large areas of maize [7,41,42], soybean [43] and wheat [44]. Therefore, most available studies were on yield estimations of maize and wheat, but few studied yield estimations of sunflower, an important economic crop in arid regions of Northwest China.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Year Mapping of Major Crop Yields in an Irrigation District from High Spatial and Temporal Resolution Vegetation Index

Shang

2018

Sensors

View full text Add to dashboard Cite

Crop yield estimation is important for formulating informed regional and national food trade policies. The introduction of remote sensing in agricultural monitoring makes accurate estimation of regional crop yields possible. However, remote sensing images and crop distribution maps with coarse spatial resolution usually cause inaccuracy in yield estimation due to the existence of mixed pixels. This study aimed to estimate the annual yields of maize and sunflower in Hetao Irrigation District in North China using 30 m spatial resolution HJ-1A/1B CCD images and high accuracy multi-year crop distribution maps. The Normalized Difference Vegetation Index (NDVI) time series obtained from HJ-1A/1B CCD images was fitted with an asymmetric logistic curve to calculate daily NDVI and phenological characteristics. Eight random forest (RF) models using different predictors were developed for maize and sunflower yield estimation, respectively, where predictors of each model were a combination of NDVI series and/or phenological characteristics. We calibrated all RF models with measured crop yields at sampling points in two years (2014 and 2015), and validated the RF models with statistical yields of four counties in six years. Results showed that the optimal model for maize yield estimation was the model using NDVI series from the 120th to the 210th day in a year with 10 days’ interval as predictors, while that for sunflower was the model using the combination of three NDVI characteristics, three phenological characteristics, and two curve parameters as predictors. The selected RF models could estimate multi-year regional crop yields accurately, with the average values of root-mean-square error and the relative error of 0.75 t/ha and 6.1% for maize, and 0.40 t/ha and 10.1% for sunflower, respectively. Moreover, the yields of maize and sunflower can be estimated fairly well with NDVI series 50 days before crop harvest, which implicated the possibility of crop yield forecast before harvest.

show abstract

Coupling Machine Learning with APSIM Model Improves the Evaluation of Climate Extremes Impact on Wheat Yield in Australia

Feng,

Wang,

Liu

et al. 2022

Modeling Processes and Their Interactions in Cropping Systems

View full text Add to dashboard Cite

Random Forests for Global and Regional Crop Yield Predictions

Cited by 513 publications

References 41 publications

Deep Learning Based Weighted SOM to Forecast Weather and Crop Prediction for Agriculture Application

Deep Learning Based Weighted SOM to Forecast Weather and Crop Prediction for Agriculture Application

Multi-Year Mapping of Major Crop Yields in an Irrigation District from High Spatial and Temporal Resolution Vegetation Index

Coupling Machine Learning with APSIM Model Improves the Evaluation of Climate Extremes Impact on Wheat Yield in Australia

Contact Info

Product

Resources

About