2021
DOI: 10.3390/rs13081519
|View full text |Cite
|
Sign up to set email alerts
|

Using a One-Dimensional Convolutional Neural Network on Visible and Near-Infrared Spectroscopy to Improve Soil Phosphorus Prediction in Madagascar

Abstract: As a proximal soil sensing technique, laboratory visible and near-infrared (Vis-NIR) spectroscopy is a promising tool for the quantitative estimation of soil properties. However, there remain challenges for predicting soil phosphorus (P) content and availability, which requires a reliable model applicable for different land-use systems to upscale. Recently, a one-dimensional convolutional neural network (1D-CNN) corresponding to the spectral information of soil was developed to considerably improve the accurac… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
40
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 42 publications
(40 citation statements)
references
References 67 publications
0
40
0
Order By: Relevance
“…In addition to using some preprocessing algorithms individually, some combinations in which the subsequent transformation supplemented the previous method were also considered. [15,[33][34][35]. In this study, a one-dimensional CNN architecture was constructed for the regression task, and its structure is shown in Figure 2.…”
Section: Data Analysis Methodsmentioning
confidence: 99%
“…In addition to using some preprocessing algorithms individually, some combinations in which the subsequent transformation supplemented the previous method were also considered. [15,[33][34][35]. In this study, a one-dimensional CNN architecture was constructed for the regression task, and its structure is shown in Figure 2.…”
Section: Data Analysis Methodsmentioning
confidence: 99%
“…Landsat-Spectroscopy Simple linear regression (SLR) Multivariate Regression Analyses [20] Reflectance resulting from spectroscopy demonstrated better estimation of soil NPK than satellite band reflectance Spectroscopy Multi Linear Regression [73] Penalized linear discriminant analysis (PLDA) applied on crop reflectance response was able to distinguish between different gradients of moisture and nitrogen induced stress. Spectroscopy PLSR, RF [25] The 1D-Convolutional Neural Network model showed a significant improvement in predicting soil P and the associated spectral wavebands.…”
Section: Findings Remote Sensing Source Modeling Approach Referencementioning
confidence: 98%
“…Rather, the attention of recent studies shifted into using remote sensing data. In fact, some have chosen the reflectance at specific wavelengths, or various indices approach (e.g., NDVI) based on hyperspectral response of soil, to indirectly predict total and extractable P, assuming the relationship between the variability of soil P concentration with soil dynamic properties associated with mechanical factors (e.g., erosion) and chemical deposits (e.g., soil organic matter) [23][24][25]. Nevertheless, other investigations tried to monitor P deficiency within crops using hyperspectral reflectance, as a method to detect responses of crop next to a specific nutrient stress such that of phosphorus [26,27].…”
Section: Introductionmentioning
confidence: 99%
“…The 1DCNN model has proved effective for soil spectroscopy [15,[27][28][29]. It requires one-dimensional data as input and uses a one-dimensional filter to construct convolutional layers.…”
Section: One-dimension Convolutional Neural Network (1dcnn)mentioning
confidence: 99%