Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review

An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping

Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: A review

Foreknowledge about sugarcane crop size can help industry members make more informed decisions. There exists many different combinations of climate variables, seasonal climate prediction indices, and crop model outputs that could prove useful in explaining sugarcane crop size. A data mining method like random forests can cope with generating a prediction model when the search space of predictor variables is large. Research that has investigated the accuracy of random forests to explain annual variation in sugarcane productivity and the suitability of predictor variables generated from crop models coupled with observed climate and seasonal climate prediction indices is limited. Simulated biomass from the APSIM (Agricultural Production Systems sIMulator) sugarcane crop model, seasonal climate prediction indices and observed rainfall, maximum and minimum temperature, and radiation were supplied as inputs to a random forest classifier and a random forest regression model to explain annual variation in regional sugarcane yields at Tully, in northeastern Australia. Prediction models were generated on 1 September in the year before harvest, and then on 1 January and 1 March in the year of harvest, which typically runs from June to November. Our results indicated that in 86.36 % of years, it was possible to determine as early as September in the year before harvest if production would be above the median. This accuracy improved to 95.45 % by January in the year of harvest. The R-squared of the random forest regression model gradually improved from 66.76 to 79.21 % from September in the year before harvest through to March in the same year of harvest. All three sets of variables—(i) simulated biomass indices, (ii) observed climate, and (iii) seasonal climate prediction indices—were typically featured in the models at various stages. Better crop predictions allows farmers to improve their nitrogen management to meet the demands of the new crop, mill managers could better plan the mill’s labor requirements and maintenance scheduling activities, and marketers can more confidently manage the forward sale and storage of the crop. Hence, accurate yield forecasts can improve industry sustainability by delivering better environmental and economic outcomes.

/pdf/accurate-prediction-of-sugarcane-yield-using-a-random-forest-zdnguae140.pdf

Accurate prediction of sugarcane yield using a random forest algorithm

Digital mapping of soil carbon fractions with machine learning

Digital mapping of soil organic matter for rubber plantation at regional scale: An application of random forest plus residuals kriging approach

Betel palms and mango plantations are two crucial commercial crops in tropical agricultural areas. Accurate spatial distributions of these two crops are essential in tropical agricultural regional planning and management. However, the characteristics of small patches, scattering, and perennation make it challenging to map betel palms and mango plantations in complex tropical agricultural regions. Furthermore, the excessive features of very-high-resolution (VHR) imaging might lead to a reduction in classification accuracy and an increase in computation times. To address these challenges, we selected five feature selection (FS) methods (random forest means a decrease in accuracy (RFMDA), ReliefF, random forest-recursive feature elimination (RFE), aggregated boosted tree (ABT), and logistic regression (LR)) and four machine learning algorithms (random forest (RF), support vector machine (SVM), classification and regression tree (CART), and adaptive boosting (AdaBoost)). Then, the optimal combinations of FS and machine learning algorithms suited for object-oriented classification of betel palms and mango plantations were explored using VHR Gaofen-2 imagery. In terms of overall accuracy, all optimal classification schemes exceeded 80%, and the classifiers using selected features increased the overall accuracy between 1% and 4% compared with classification without FS methods. Specifically, LR was appropriate to RF and SVM classifiers, which produced the highest classification accuracy (89.1% and 89.88% for RF and SVM, respectively). In contrast, ABT and ReliefF were found to be suitable FS methods for CART and AdaBoost classifiers, respectively. Overall, all four optimal combinations of FS methods and classifiers could precisely recognize mango plantations, whereas betel palms were best depicted by using the RF-LR method with 26 features. The results indicated that combination of feature selection and machine learning algorithms contributed to the object-oriented classification of complex tropical crops using Gaofen-2 imagery, which provide a useful methodological reference for precisely recognizing small tropical agricultural patterns.

/pdf/combinations-of-feature-selection-and-machine-learning-3uvuq40u.pdf

Combinations of Feature Selection and Machine Learning Algorithms for Object-Oriented Betel Palms and Mango Plantations Classification Based on Gaofen-2 Imagery

Estimating foliar phosphorus of rubber trees using locally modelling approach with hyperspectral reflectance

https://doi.org/10.1016/j.heliyon.2022.e09795

A local model based on environmental variables clustering for estimating foliar phosphorus of rubber trees with vis-NIR spectroscopic data

Abstract. The leaf area index (LAI) is an important parameter for describing the growth status and canopy structure of vegetation. The rapid and accurate acquisition of the vegetation or agroforestry LAI has great scientific significance in agroforestry ecological ecosystems research and a very important practical value for guiding agricultural and forestry production. In this study, the typical tropical crops (rubber forest) in Hainan Island were selected as the research area, the empirical and neural network (NN) LAI estimation models of rubber forest were constructed based on satellite remote sensing vegetation indices and the field LAI measurement data, and the spatiotemporal variation was analyzed. The results showed that, compared with normalized difference vegetation index (NDVI), green NDVI (GNDVI), ratio VI (RVI), normalized near-infrared (NNIR), wide dynamic range VI (WDRVI), and normalized difference water index (NDWI), enhanced vegetation index (EVI), soil adjusted vegetation index (SAVI), DVI, renormalized DVI (RDVI), and modified SAVI (MSAVI) have higher correlations with LAI. Among the LAI estimation models of rubber forest based on empirical and artificial NN (ANN) models, the estimation accuracy of ANN achieves the highest value. The linear fitting determination coefficient R2 of the observed and simulated rubber forest LAI was 0.85 (p  <  0.001), the root mean square error (RMSE) was 0.15, and the average relative error (RE) was 1.93%. However, there was underestimation in the middle-value area and overestimation in the high- and low-value areas of LAI. Based on remote sensing mapping of the rubber forest LAI, the high LAI values (4.40 to 6.00  m2 m  −  2) were mainly distributed in Danzhou and Baisha (west of Hainan Island); the middle LAI values (3.80 to 4.40  m2 m  −  2) were mainly located in Chengmai, Tunchang, and Qiongzhong (middle of Hainan Island); and the low LAI values (<3.80  m2 m  −  2) were shown primarily on Ding’an, Qionghai, Wanning, Ledong, and Sanya (east and south of Hainan Island). In summary, the remote sensing estimation model for the rubber plantation LAI based on the vegetation index has high accuracy and good values for application.

Mao-Fen Li

Papers

Digital mapping of soil organic matter for rubber plantation at regional scale: An application of random forest plus residuals kriging approach

Combinations of Feature Selection and Machine Learning Algorithms for Object-Oriented Betel Palms and Mango Plantations Classification Based on Gaofen-2 Imagery

Estimating foliar phosphorus of rubber trees using locally modelling approach with hyperspectral reflectance

A local model based on environmental variables clustering for estimating foliar phosphorus of rubber trees with vis-NIR spectroscopic data

Retrieving leaf area index of rubber plantation in Hainan Island using empirical and neural network models with Landsat images