Soil organic carbon (SOC) prediction in Australian sugarcane fields using Vis–NIR spectroscopy with different model setting approaches

Zhao, Xueyu; Zhao, Dongxue; Wang, Jie; Triantafilis, John

doi:10.1016/j.geodrs.2022.e00566

Cited by 15 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies using Vis-NIR and pXRF together to predict soil OC have shown their applicability regardless of soil texture variability (Weindorf & Chakraborty, 2018), but testing using multinational datasets have not yet been completed. Zhao et al (2022) successfully applied Vis-NIR to assess soil OC in 639 samples in four sugarcane districts in Australia (R 2 > 0.7). Samples included five soil reference groups (Spaargaren & Deckers, 1998).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Multinational prediction of soil organic carbon and texture via proximal sensors

Mancini,

Andrade,

Silva

et al. 2023

Soil Science Soc of Amer J

View full text Add to dashboard Cite

Novel technologies help to monitor environmental impact of human activities, but tests involving datasets from several countries, encompassing a large variability of soil properties, are still scarce. This study utilized proximal sensors to predict soil organic carbon (OC) and soil texture of samples from Brazil, France, India, Mozambique, and United States of America. In total, 1,749 samples were analyzed by portable X‐ray fluorescence spectrometry (pXRF) and visible near‐infrared diffuse reflectance spectroscopy (Vis‐NIR). Samples were randomly split into modeling (70%) and validation (30%) datasets. Sand (R2 = 0.82), silt (0.87) and clay (0.84) predictions were very accurate, despite contrasting climates, soil parent materials, and weathering degrees. Soil OC predictions were similarly successful (0.72). pXRF was the optimal sensor for soil texture predictions. Proximal soil sensing can be successfully used with a global soil database offering a clean, rapid, and accurate alternative to estimate soil texture and OC across the globe.This article is protected by copyright. All rights reserved

show abstract

Section: Discussionmentioning

confidence: 99%

“…Zhao et al. (2022) successfully applied Vis‐NIR to assess soil OC in 639 samples in four sugarcane districts in Australia ( R 2 > 0.7). Samples included five soil reference groups (Spaargaren & Deckers, 1998).…”

Section: Discussionmentioning

confidence: 99%

Multinational prediction of soil organic carbon and texture via proximal sensors

Mancini,

Andrade,

Silva

et al. 2023

Soil Science Soc of Amer J

View full text Add to dashboard Cite

show abstract

“…This research is the first step toward reversing the significant economic impact of SEC on Canadian agriculture, as well as encouraging the scientific community to pursue detailed research on developing new methodologies to distinguish accurately between SEC and crop yield costs from other important variables such as crop rotation, pathogens, crop nutrient uptake (i.e., nutrient stewardship), and climate impacts (e.g., drought). We suggest incorporating advanced remote sensing technologies, such as proximal soil sensing using soil-spectroscopy-based approaches, to assess SOC dynamics and their relationship with spatiotemporal crop yield variability [36][37][38][39]. Also, there have been recent advances in remote sensing technology for modeling large-scale SOC dynamics to generate accurate geospatial datasets of soil-erosion-related physical and chemical properties [40][41][42].…”

Section: Discussionmentioning

confidence: 99%

The Costs of Soil Erosion to Crop Production in Canada between 1971 and 2015

Badreldin

Lobb

2023

Sustainability

View full text Add to dashboard Cite

Canada is known for its massive and fertile landscape, and one of the biggest industries in Canada is crop production, which is responsible for contributing to the national economy as well as the global food supply. Soil erosion is considered the top challenge facing Canadian farmers in the 21st century. This study aims to evaluate soil erosion’s impact on Canadian crop production, assessed based on the integration of soil erosion analysis and multitemporal crop market values from 1971 to 2015. Soil Erosion Risk Indicator models were used to assess soil erosion’s impact on crop productivity using the relationship of soil organic carbon with crop yield gain/loss. The total soil erosion cost of yield losses in the 44 years leading up to 2015 is estimated to be CAD 33.51 billion. 2013 was found to show the highest loss, with CAD 1.93 billion. Oilseeds, small grains, and potatoes were the major crop commodities that were impacted by yield loss as a direct result of soil erosion, the costs being 41%, 37%, and 15%, respectively. Ontario and Saskatchewan were the most impacted provinces, with costs of 45.25% and 22.50%, respectively. Four eras were detected in this research, each having unique soil erosion costs, which reflect different agriculture policy and soil conservation efforts: Era 1 (1971–1988), Era 2 (1989–1995), Era 3 (1996–2007), and Era 4 (2008–2015). This research is the beginning of exploring the cost of the environmental impacts on agriculture sustainability in Canada and supporting decision makers in adopting effective soil conservation strategies to mitigate these impacts.

show abstract

“…The CCC represents how close a model prediction conforms to the ground truth data along a 45 degree line from the origin. For the CCC, there is an excellent model with CCC > 0.8, a moderate model with 0.8 > CCC > 0.65 and a poor model with CCC < 0.65 [24]. For predicting the TSS based on MSC+SG spectral preprocessing, the PLSR presented an RMSE, R 2 , RPD and CCC of 0.554 • Brix, 0.583, 1.54 and 0.693, respectively.…”

Section: Predictive Model Performance Based On Regression Modelsmentioning

confidence: 94%

Hyperspectral Imaging Spectroscopy for Non-Destructive Determination of Grape Berry Total Soluble Solids and Titratable Acidity

Lyu,

Grafton,

Ramilan

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Wine grape quality heavily influences the price received for a product. Hyperspectral imaging has the potential to provide a non-destructive technique for predicting various enological parameters. This study aims to explore the feasibility of applying hyperspectral imaging to measure the total soluble solids (TSS) and titratable acidity (TA) in wine grape berries. A normalized difference spectral index (NDSI) spectral preprocessing method was built and compared with the conventional preprocessing method: multiplicative scatter correction and Savitzky–Golay smoothing (MSC+SG). Different machine learning models were built to examine the performance of the preprocessing methods. The results show that the NDSI preprocessing method demonstrated better performance than the MSC+SG preprocessing method in different classification models, with the best model correctly classifying 93.8% of the TSS and 84.4% of the TA. In addition, the TSS can be predicted with moderate performance using support vector regression (SVR) and MSC+SG preprocessing with a root mean squared error (RMSE) of 0.523 °Brix and a coefficient of determination (R2) of 0.622, and the TA can be predicted with moderate performance using SVR and NDSI preprocessing (RMSE = 0.19%, R2 = 0.525). This study demonstrates that hyperspectral imaging data and NDSI preprocessing have the potential to be a method for grading wine grapes for producing quality wines.

show abstract

Soil organic carbon (SOC) prediction in Australian sugarcane fields using Vis–NIR spectroscopy with different model setting approaches

Cited by 15 publications

References 35 publications

Multinational prediction of soil organic carbon and texture via proximal sensors

Multinational prediction of soil organic carbon and texture via proximal sensors

The Costs of Soil Erosion to Crop Production in Canada between 1971 and 2015

Hyperspectral Imaging Spectroscopy for Non-Destructive Determination of Grape Berry Total Soluble Solids and Titratable Acidity

Contact Info

Product

Resources

About