scholarly journals Prediction of Soil Nutrient Contents Using Visible and Near-Infrared Reflectance Spectroscopy

2019 ◽  
Vol 8 (10) ◽  
pp. 437 ◽  
Author(s):  
Yiping Peng ◽  
Li Zhao ◽  
Yueming Hu ◽  
Guangxing Wang ◽  
Lu Wang ◽  
...  
Keyword(s):  
Near Infrared ◽  
Regional Scale ◽  
Soil Nutrient ◽  
Hyperspectral Data ◽  
Estimation Accuracy ◽  
Soil Productivity ◽  
Least Squares Regression ◽  
Near Infrared Reflectance ◽  
Nutrient Contents ◽  
Soil Nutrient Contents

Quickly and efficiently monitoring soil nutrient contents using remote sensing technology is of great significance for farmland soil productivity, food security and sustainable agricultural development. Current research has been conducted to estimate and map soil nutrient contents in large areas using hyper-spectral techniques, however, it is difficult to obtain accurate estimates. In order to improve the estimation accuracy of soil nutrient contents, we introduced a GA-BPNN method, which combined a back propagation neural network (BPNN) with the genetic algorithm optimization (GA). This study was conducted in Guangdong, China, based on soil nutrient contents and hyperspectral data. The prediction accuracies from a partial least squares regression (PLSR), BPNN and GA-BPNN were compared using field observations. The results showed that (1) Among three methods, the GA-BPNN provided the most accurate estimates of soil total nitrogen (TN), total phosphorus (TP) and total potassium (TK) contents; (2) Compared with the BPNN models, the GA-BPNN models significantly improved the estimation accuracies of the soil nutrient contents by decreasing the relative root mean square error (RRMSE) values by 15.9%, 5.6% and 20.2% at the sample point level, and 20.1%, 16.5% and 47.1% at the regional scale for TN, TP and TK, respectively. This indicated that by optimizing the parameters of BPNN, the GA-BPNN provided greater potential to improving the estimation; and (3) Soil TK content could be more accurately mapped by the GA-BPNN method using HuanJing-1A Hyperspectral Imager (HJ-1A HSI) (manufacturer: China Aerospace Science and Technology Corporation; Beijing, China) data with a RRMSE value of 20.37% than the soil TN and TP with the RRMSE values of 40.41% and 34.71%, respectively. This implied that the GA-BPNN model provided the potential to map the soil TK content for the large area. The research results provided an important reference for high-accuracy prediction of soil nutrient contents.

Predicting soil nutrient contents using Landsat OLI satellite images in rain-fed agricultural lands, northwest of Iran

2021 ◽  
Vol 193 (9) ◽  
Author(s):  
Naser Miran ◽  
Mir Hassan Rasouli Sadaghiani ◽  
Vali Feiziasl ◽  
Ebrahim Sepehr ◽  
Mehdi Rahmati ◽  
...  
Keyword(s):  
Satellite Images ◽  
Soil Nutrient ◽  
Agricultural Lands ◽  
Nutrient Contents ◽  
Northwest Of Iran ◽  
Soil Nutrient Contents

scholarly journals Effects of Planting Density on Soil Bulk Density, pH and Nutrients of Unthinned Chinese Fir Mature Stands in South Subtropical Region of China

Forests ◽  
2019 ◽  
Vol 10 (4) ◽  
pp. 351
Author(s):  
Aiguo Duan ◽  
Jie Lei ◽  
Xiaoyan Hu ◽  
Jianguo Zhang ◽  
Hailun Du ◽  
...  
Keyword(s):  
Organic Matter ◽  
Bulk Density ◽  
Soil Depth ◽  
Soil Nutrient ◽  
Chinese Fir ◽  
Planting Density ◽  
Total N ◽  
Nutrient Contents ◽  
Exchangeable Ca ◽  
Soil Nutrient Contents

Chinese fir (Cunninghamia lanceolata (Lamb.) Hook) is a fast-growing evergreen conifer with high-quality timber and is an important reforestation and commercial tree species in southern China. Planting density affects the productivity of Chinese fir plantations. To study the effect of five different planting densities and soil depth on soil nutrient contents of a mature C. lanceolata plantation, the soil nutrient contents (soil depths 0–100 cm) of 36-year-old mature Chinese fir plantations under five different planting densities denoted A (1667 trees·ha−1), B (3333 trees·ha−1), C (5000 trees·ha−1), D (6667 trees·ha−1), and E (10,000 trees·ha−1) were measured in Pingxiang county, Guangxi province, China. Samples were collected from the soil surface down to a one meter depth from each of 45 soil profiles, and soil samples were obtained at 10 different soil depths of 0–10, 10–20, 20–30, 30–40, 40–50, 50–60, 60–70, 70–80, 80–90, and 90–100 cm. Twelve soil physical and chemical indicators were analyzed. The results showed that: (1) as planting density increased, the organic matter, organic carbon, total N and P, available N, effective Fe, and bulk density decreased. Soil pH, total K, and effective K increased with increasing planting density. Planting density did not significantly influence the exchangeable Ca and Mg. (2) Soil organic matter; organic carbon; total N and P; effective N, P, and K; exchangeable Ca and Mg; effective Fe content; and bulk density decreased with increasing soil depth. This pattern was particularly evident in the top 30 cm of the soil. (3) Excessively high planting density is not beneficial to the long-term maintenance of soil fertility in Chinese fir plantations, and the planting density of Chinese fir plantations should be maintained below 3333 stems·ha−1 (density A or B) to maintain soil fertility while ensuring high yields.

scholarly journals Mapping Soil Alkalinity and Salinity in Northern Songnen Plain, China with the HJ-1 Hyperspectral Imager Data and Partial Least Squares Regression

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3855 ◽  
Author(s):  
Lin Bai ◽  
Cuizhen Wang ◽  
Shuying Zang ◽  
Changshan Wu ◽  
Jinming Luo ◽  
...  
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Soil Ph ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Hyperspectral Data ◽  
Validation Dataset ◽  
Least Squares Regression ◽  
Songnen Plain ◽  
Mean Square Errors

In arid and semi-arid regions, identifying and monitoring of soil alkalinity and salinity are in urgently need for preventing land degradation and maintaining ecological balances. In this study, physicochemical, statistical, and spectral analysis revealed that potential of hydrogen (pH) and electrical conductivity (EC) characterized the saline-alkali soils and were sensitive to the visible and near infrared (VIS-NIR) wavelengths. On the basis of soil pH, EC, and spectral data, the partial least squares regression (PLSR) models for estimating soil alkalinity and salinity were constructed. The R2 values for soil pH and EC models were 0.77 and 0.48, and the root mean square errors (RMSEs) were 0.95 and 17.92 dS/m, respectively. The ratios of performance to inter-quartile distance (RPIQ) for the soil pH and EC models were 3.84 and 0.14, respectively, indicating that the soil pH model performed well but the soil EC model was not considerably reliable. With the validation dataset, the RMSEs of the two models were 1.06 and 18.92 dS/m. With the PLSR models applied to hyperspectral data acquired from the hyperspectral imager (HSI) onboard the HJ-1A satellite (launched in 2008 by China), the soil alkalinity and salinity distributions were mapped in the study area, and were validated with RMSEs of 1.09 and 17.30 dS/m, respectively. These findings revealed that the hyperspectral images in the VIS-NIR wavelengths had the potential to map soil alkalinity and salinity in the Songnen Plain, China.

scholarly journals Estimating Soil Arsenic Content with Visible and Near-Infrared Hyperspectral Reflectance

2020 ◽  
Vol 12 (4) ◽  
pp. 1476 ◽  
Author(s):  
Lei Han ◽  
Rui Chen ◽  
Huili Zhu ◽  
Yonghua Zhao ◽  
Zhao Liu ◽  
...  
Keyword(s):  
Near Infrared ◽  
Back Propagation ◽  
Hyperspectral Data ◽  
Pollution Monitoring ◽  
World Health ◽  
Support Vector ◽  
Inversion Method ◽  
Arsenic Content ◽  
Least Squares Regression ◽  
Soil Arsenic

Soil arsenic (AS) contamination has attracted a great deal of attention because of its detrimental effects on environments and humans. AS and inorganic AS compounds have been classified as a class of carcinogens by the World Health Organization. In order to select a high-precision method for predicting the soil AS content using hyperspectral techniques, we collected 90 soil samples from six different land use types to obtain the soil AS content by chemical analysis and hyperspectral data based on an indoor hyperspectral experiment. A partial least squares regression (PLSR), a support vector regression (SVR), and a back propagation neural network (BPNN) were used to establish a relationship between the hyperspectral and the soil AS content to predict the soil AS content. In addition, the feasibility and modeling accuracy of different interval spectral resampling, different spectral pretreatment methods, feature bands, and full-band were compared and discussed to explore the best inversion method for estimating soil AS content by hyperspectral. The results show that 10 nm + second derivative (SD) + BPNN is the optimum method to predict soil AS content estimation; R v 2 is 0.846 and residual predictive deviation (RPD) is 2.536. These results can expand the representativeness and practicability of the model to a certain extent and provide a scientific basis and technical reference for soil pollution monitoring.

scholarly journals Using Near-infrared reflectance spectroscopy (NIRS) to predict glucobrassicin concentrations in cabbage and brussels sprout leaf tissue

Plant Methods ◽  
2020 ◽  
Vol 16 (1) ◽  
Author(s):  
Ilse E. Renner ◽  
Vincent A Fritz
Keyword(s):  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Leaf Tissue ◽  
Reflectance Spectroscopy ◽  
Infrared Reflectance ◽  
Least Squares Regression ◽  
Near Infrared Reflectance Spectroscopy ◽  
Near Infrared Reflectance ◽  
Brussels Sprouts ◽  
Freeze Dried

Abstract Background Glucobrassicin (GBS) and its hydrolysis product indole-3-carbinol are important nutritional constituents implicated in cancer chemoprevention. Dietary consumption of vegetables sources of GBS, such as cabbage and Brussels sprouts, is linked to tumor suppression, carcinogen excretion, and cancer-risk reduction. High-performance liquid-chromatography (HPLC) is the current standard GBS identification method, and quantification is based on UV-light absorption in comparison to known standards or via mass spectrometry. These analytical techniques require expensive equipment, trained laboratory personnel, hazardous chemicals, and they are labor intensive. A rapid, nondestructive, inexpensive quantification method is needed to accelerate the adoption of GBS-enhancing production systems. Such an analytical method would allow producers to quantify the quality of their products and give plant breeders a high-throughput phenotyping tool to increase the scale of their breeding programs for high GBS-accumulating varieties. Near-infrared reflectance spectroscopy (NIRS) paired with partial least squares regression (PLSR) could be a useful tool to develop such a method. Results Here we demonstrate that GBS concentrations of freeze-dried tissue from a wide variety of cabbage and Brussels sprouts can be predicted using partial least squares regression from NIRS data generated from wavelengths between 950 and 1650 nm. Cross-validation models had R2 = 0.75 with RPD = 2.3 for predicting µmol GBS·100 g−1 fresh weight and R2 = 0.80 with RPD = 2.4 for predicting µmol GBS·g−1 dry weight. Inspections of equation loadings suggest the molecular associations used in modeling may be due to first overtones from O–H stretching and/or N–H stretching of amines. Conclusions A calibration model suitable for screening GBS concentration of freeze-dried leaf tissue using NIRS-generated data paired with PLSR can be created for cabbage and Brussels sprouts. Optimal NIRS wavelength ranges for calibration remain an open question.

scholarly journals Mapping Canopy Chlorophyll Content in a Temperate Forest Using Airborne Hyperspectral Data

2020 ◽  
Vol 12 (21) ◽  
pp. 3573
Author(s):  
J. Malin Hoeppner ◽  
Andrew K. Skidmore ◽  
Roshanak Darvishzadeh ◽  
Marco Heurich ◽  
Hsing-Chung Chang ◽  
...  
Keyword(s):  
Chlorophyll Content ◽  
Spectral Resolution ◽  
Near Infrared ◽  
Deciduous Forest ◽  
Mixed Forest ◽  
Hyperspectral Data ◽  
Least Squares Regression ◽  
Area Index ◽  
Management Interventions ◽  
Shortwave Infrared

Chlorophyll content, as the primary pigment driving photosynthesis, is directly affected by many natural and anthropogenic disturbances and stressors. Accurate and timely estimation of canopy chlorophyll content (CCC) is essential for effective ecosystem monitoring to allow for successful management interventions to occur. Hyperspectral remote sensing offers the possibility to accurately estimate and map canopy chlorophyll content. In the past, research has predominantly focused on the use of hyperspectral data on canopy chlorophyll content retrieval of crops and grassland ecosystems. Therefore, in this study, a temperate mixed forest, the Bavarian Forest National Park in Germany, was chosen as the study site. We compared different statistical models (narrowband vegetation indices (VIs), partial least squares regression (PLSR) and random forest (RF)) in their accuracy to predict CCC using airborne hyperspectral data. The airborne hyperspectral imagery was acquired by the AisaFenix sensor (623 bands; 3.5 nm spectral resolution in the visible near-infrared (VNIR) region, and 12 nm spectral resolution in the shortwave infrared (SWIR) region; 3 m spatial resolution) on July 6, 2017. In situ leaf chlorophyll content and leaf area index measurements were sampled from the upper canopy of coniferous, mixed, and deciduous forest stands in July and August 2017. The study yielded the highest retrieval accuracies with PLSR (root mean square error (RMSE) = 0.25 g/m2, R2 = 0.66). It further indicated specific spectral regions within the visible (390–400 nm and 470–540 nm), red edge (680–780 nm), near-infrared (1050–1100 nm) and shortwave infrared regions (2000–2270 nm) that were important for CCC retrieval. The results showed that forest CCC can be mapped with relatively high accuracies using image spectroscopy.

The Application of GIS Techniques in Soil Testing and Fertilizer Recommendations: Part II the Distribution of Soil Nutrients in Hainan, China

2012 ◽  
Vol 610-613 ◽  
pp. 3697-3701
Author(s):  
Zhi Yuan Wei ◽  
Deng Feng Wang ◽  
Zhi Ping Qi
Keyword(s):  
Spatial Analysis ◽  
Soil Nutrients ◽  
Arable Land ◽  
Soil Nutrient ◽  
Hainan Island ◽  
Nutrient Elements ◽  
Available N ◽  
Nutrient Contents ◽  
Fertilizer Recommendations ◽  
Soil Nutrient Contents

The research on the distribution of soil nutrient contents in arable land regionally is the basis for the proper fertilization. The study, taking Hainan Island as the study area, analyzes the distribution and variation of soil nutrient contents in arable land spatially and temporally by applying GIS spatial analysis. As the study shows, from the 1980s to the year of 2005, the TN, TP, TK, and Available N contents in soil of arable land have declined to certain degree, while Available P and Available K kept increasing. Generally, the soil nutrients have declined in quality during last two decades but remain in a mediate level. Spatial analysis can reflect the distribution characteristics of the regional soil nutrient elements in an objective manner.

scholarly journals Decomposition characteristics of long-established Salix psammophila sand barriers in an arid area, Northwestern China

BioResources ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. 5947-5963
Author(s):  
Ruidong Wang ◽  
Xia Yang ◽  
Yong Gao ◽  
Xiaohong Dang ◽  
Yumei Liang ◽  
...  
Keyword(s):  
Nutrient Release ◽  
Soil Nutrient ◽  
Decomposition Process ◽  
Northwestern China ◽  
Barrier Material ◽  
Nutrient Contents ◽  
Arid Northwestern China ◽  
Decomposition Time ◽  
Soil Nutrient Contents

Salix psammophila has been extensively used as a sand barrier material for various desertification control applications. Elucidating the long-term decomposition characteristics and nutrient cycling process of this sand barrier in desert environments is of great importance. In this study, which was conducted for 1 to 9 years, changes in the mass loss percentage and the residual percentage in the decomposition process were explored of S. psammophila sand barriers in arid Northwestern China. In addition, the S. psammophila analysis nutrient elements release rule and its influence on soil properties were evaluated. The results showed that the decomposition process of S. psammophila sand barriers exhibited a “slow-fast” trend. After decomposition time for 9 years, mass decreased remarkably, and the residual percentage was 33.6%. Further, the nutrient release characteristics differed. C, P, and K were in the release state, whereas N was in the enrichment state. The decomposition percentage of the sand barriers was significantly correlated with N, P, K, C/N, C/P, and N/P (p < 0.05). The soil nutrient contents of C, P, and K contents increased 3.43, 2.23, and 2.08 g/kg compared to the initial values, respectively. The soil nutrient contents of N contents decreased 0.19 g/kg.

scholarly journals Machine Learning Algorithms for Soil Properties Prediction with Treated Vis–NIR Spectrums from the Itatiaia National Park

2019 ◽  
Author(s):  
Yuri Andrei Gelsleichter ◽  
Lúcia Helena Cunha dos Anjos ◽  
Elias Mendes Costa ◽  
Gabriela Valente ◽  
Paula Debiasi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Properties ◽  
National Park ◽  
Near Infrared ◽  
Learning Algorithms ◽  
Management Plan ◽  
Machine Learning Algorithms ◽  
Total Carbon ◽  
Least Squares Regression ◽  
Near Infrared Reflectance

Visible and near-infrared reflectance (Vis&ndash;NIR) techniques are a plausible method to soil analyses. The main objective of the study was to investigate the capacity to predicting soil properties Al, Ca, K, Mg, Na, P, pH, total carbon (TC), H and N, by using different spectral (350&ndash;2500 nm) pre-treatments and machine learning algorithms such as Artificial Neural Network (ANN), Random Forest (RF), Partial Least-squares Regression (PLSR) and Cubist (CB). The 300 soil samples were sampled in the upper part of the Itatiaia National Park (INP), located in Southeastern region of Brazil. The 10 K-fold cross validation was used with the models. The best spectral pre-treatment was the Inverse of Reflectance by a Factor of 104 (IRF4) for TC with CB, giving an averaged R&sup2; among the folds of 0.85, RMSE of 1.96; and 0.67 with 0.041 respectively for H. Into the K-folds models of TC, the highest prediction had a R&sup2; of 0.95. These results are relevant for the INP management plan, and also to similar environments. The good correlation with Vis&ndash;NIR techniques can be used for remote sense monitoring, especially in areas with very restricted access such as INP.

Sign in / Sign up

Export Citation Format

Share Document