A robust method to estimate foliar phosphorus of rubber trees with hyperspectral reflectance

Shi, Zhou; Li, Mao-Fen; Luo, Wei; Zhengzao, Cha

doi:10.1016/j.indcrop.2018.09.055

Cited by 19 publications

(13 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The artificial neural networks (ANNs) that are inspired by biological neural network are also frequently used tools for various fields [11–13]. ANNs can deal with both linear and non-linear relationships between variables [11, 12]. In the current study, ANNs with three layers (an input, a hidden, and an output layers) were tested and trained with scale conjugate gradient back propagation algorithm (Fig 2).…”

Section: Methodsmentioning

confidence: 99%

Estimation of soil pH with geochemical indices in forest soils

Liu

2019

PLoS ONE

View full text Add to dashboard Cite

Soil pH is a critical soil quality index and controls soil microbial activities, soil nutrient availability, and plant roots growth and development. The current study aims to evaluate various pedotransfer functions for predicting soil pH using different geochemical indices (CaO, ratios of Al2O3, Fe2O3, TiO2, SiO2, MgO, and K2O to CaO) in forest soils. Various models including empirical functions (quadratic, cubic, sigmoid, logarithmic) and artificial neural network with these geochemical indices were assessed by independent testing set. Mean bias error (MBE), root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), coefficient of determination (R2), t-statistics (t-stat), and Akaike’s Information Criterion (AIC) were applied to evaluate the model performances. Additionally, a new indicator (global performance indictor, GPI) was originally introduced in this study and was used to rank these models. According to GPI, the sigmoid functions and ANNs performed better than others. On average, they could explain above 70% of the variability in soil pH. Both model structure and dataset shape impact on model performance. The best input was CaO for ANNs, sigmoid, and logarithmic functions. The ratios of K2O to CaO and Al2O3 to CaO were the best inputs for quadratic and cubic equations, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Estimation of soil pH with geochemical indices in forest soils

Liu

2019

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Chilling damage is usually accompanied by long-term secondary damage of the rubber plantation, such as tree dieback, bark splitting, and bleeding [2]. To determine the wind resistance performance index of rubber trees and cultivate strong, resistant varieties, an accurate algorithm for individual rubber tree segmentation is indispensable for obtaining the structural parameters and dynamic change information of rubber trees of different clones [3].…”

Section: Introductionmentioning

confidence: 99%

“…r (recall): tree crown detection rate. 2 P (precision): the correctness of the detected tree 3. F (F-score): the overall accuracy of detected tree.…”

mentioning

confidence: 99%

Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Wang

Chen

Cao

et al. 2019

Forests

View full text Add to dashboard Cite

Rubber trees in southern China are often impacted by natural disturbances that can result in a tilted tree body. Accurate crown segmentation for individual rubber trees from scanned point clouds is an essential prerequisite for accurate tree parameter retrieval. In this paper, three plots of different rubber tree clones, PR107, CATAS 7-20-59, and CATAS 8-7-9, were taken as the study subjects. Through data collection using ground-based mobile light detection and ranging (LiDAR), a voxelisation method based on the scanned tree trunk data was proposed, and deep images (i.e., images normally used for deep learning) were generated through frontal and lateral projection transform of point clouds in each voxel with a length of 8 m and a width of 3 m. These images provided the training and testing samples for the faster region-based convolutional neural network (Faster R-CNN) of deep learning. Consequently, the Faster R-CNN combined with the generated training samples comprising 802 deep images with pre-marked trunk locations was trained to automatically recognize the trunk locations in the testing samples, which comprised 359 deep images. Finally, the point clouds for the lower parts of each trunk were extracted through back-projection transform from the recognized trunk locations in the testing samples and used as the seed points for the region’s growing algorithm to accomplish individual rubber tree crown segmentation. Compared with the visual inspection results, the recognition rate of our method reached 100% for the deep images of the testing samples when the images contained one or two trunks or the trunk information was slightly occluded by leaves. For the complicated cases, i.e., multiple trunks or overlapping trunks in one deep image or a trunk appearing in two adjacent deep images, the recognition accuracy of our method was greater than 90%. Our work represents a new method that combines a deep learning framework with point cloud processing for individual rubber tree crown segmentation based on ground-based mobile LiDAR scanned data.

show abstract

“…Peng et al performed prediction of salt concentrations in soil, using PLSR and training a support vector machine on the reduced representation. Li et al and Guo et al [11], [12] propose using a repeated subsampling (similar to bagging) to reject all wavelengths that are not consistently identified as informative, followed by a PCA-like procedure that selects features that allow for the largest projection into a plane orthogonal to the already selected features. They report that they can reduce the full descriptor space from 2151 wavelengths to 31, and further to 7 via multiple linear regression, and that this approach outperforms selection by PLSR.…”

Section: Related Workmentioning

confidence: 99%

Using Data Science to Improve the Identification of Plant Nutritional Status

Condaminet

Zimmermann

Billiot³

et al. 2020

2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

Developing products for improving plant nutritional status, e.g. fertilizers or plant growth regulators, is an important topic to move towards sustainability in agriculture and to ensure to feed the world population. A key challenge is to identify when, what, and how much nutrients to add to plants' growth environment. In this paper, we study a use case on how to characterize rapeseed plant nutrient deficiencies during their growth. A promising approach consists of deriving data from spectroscopy of leaves, and using this representation to predict what kind of deficiency (if any) plants are undergoing. We are considering three research questions: 1) from which day after onset of a nutrient deficiency we can identify it, 2) whether leaves that have sprouted under nutrient-rich conditions can still help in identifying problems. Third, and most importantly, performing the spectroscopy on the full range of wavelengths is expensive, which under production conditions allows for only relatively few samples. We therefore explore how to perform dimensionality reduction and preprocessing to achieve good predictive accuracy. We show that 1) deficiencies can be identified early on, 2) leaf generations help to predict nutrient deficiencies, and 3) that preprocessing increases the accuracy and dimensionality reduction can be performed without loss of accuracy. Along the way, we find that our some of our industry partners' assumptions about the data do not seem to be borne out by our empirical results, and that the subset of data they initially selected turns out to be too easy to model. The full data leads to more informative insights.

show abstract

A robust method to estimate foliar phosphorus of rubber trees with hyperspectral reflectance

Cited by 19 publications

References 77 publications

Estimation of soil pH with geochemical indices in forest soils

Estimation of soil pH with geochemical indices in forest soils

Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Using Data Science to Improve the Identification of Plant Nutritional Status

Contact Info

Product

Resources

About