Development of a Swiss National Soil Spectral Model Library using data-driven modeling

2020 ◽  
Author(s):  
Philipp Baumann ◽  
Anatol Helfenstein ◽  
Andreas Gubler ◽  
Reto Meuli ◽  
Armin Keller ◽  
...  
Keyword(s):  
Soil Properties ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Monitoring Network ◽  
Total Carbon ◽  
Data Driven ◽  
Local Approach ◽  
Organic C ◽  
Soil C ◽  
Over Time

<p>Soil data at different scales are needed for assessments and monitoring of soil functions. Soil diffuse reflectance spectroscopy using visible–Near Infrared and mid-Infrared energies can be used to estimate a range of soil properties, rapidly and inexpensively. However the spectroscopic modeling is challenging because of the large soil diversity and its complex composition. We developed a National Soil Spectral library (SSL) (n = 4339) using samples from (i) the Swiss Soil Monitoring Network (NABO; 7 sampling campaigns at 71 agricultural locations since 1985, n = 592) and (ii) the National Biodiversity Monitoring (BDM) Program (n = 4295, 1094 locations across a 5x5 km grid). The SSL will provide spectroscopic models for estimation of functional soil properties at different scales (e.g. total carbon (C) and nitrogen, organic C, texture, pH and cation exchange capacity). We used a rule-based algorithm, Cubist, for the modelling. The models were tuned across full combinations of {5, 10, 20, 50, 100} committees and {2, 5, 7, 9} neighbors, using 5 times repeated 10-fold cross-validation grouped by location. Further, transfer learning with RS-LOCAL tuning was performed for each of the 71 monitoring sites separately by a hold out approach in order to select optimal instances from the remaining SSL. Total soil C in the reference data ranged from 0.1% to 58.3% C and the best Cubist model had a cross-validated RMSE of 0.82% C. The RS-LOCAL approach (RMSE<sub>mean</sub> = 0.14 %) was on average 2.5 times more accurate for the estimation of C over time at each of the 71 NABO sites compared to the general Cubist approach. Our results suggest that data-driven selection of SSL instances targeted to closely related soils produces less biased estimation of soil properties over time at smaller geographic extents. The general Cubist calibration models are useful when reference analyses in a new study area are scarce. In conclusion, the Swiss SSL models can be used to cost-efficiently estimate a range of soil properties for a diverse applications and purposes in Switzerland.</p>

scholarly journals Developing the Swiss soil spectral library for local estimation and monitoring

2021 ◽  
Author(s):  
Philipp Baumann ◽  
Anatol Helfenstein ◽  
Andreas Gubler ◽  
Armin Keller ◽  
Reto Giulio Meuli ◽  
...  
Keyword(s):  
Soil Properties ◽  
Chemical Diversity ◽  
Total Carbon ◽  
Data Driven ◽  
Organic Soils ◽  
Spectral Library ◽  
Total N ◽  
Organic C ◽  
Measured Range

Abstract. Information on soils' composition and physical, chemical and biological properties is paramount to elucidate agroecosystem functioning in space and over time. For this purposes we developed a national Swiss soil spectral library (SSL; n = 4374) in the mid-infrared (mid-IR), calibrating 17 properties from legacy measurements on soils from the Swiss biodiversity monitoring program (n = 3778; 1094 sites) and the Swiss long-term monitoring network (n = 596; 71 sites). General models were trained with the interpretable rule-based learner CUBIST, testing combinations of {5, 10, 20, 50, 100} committees of rules and {2, 5, 7, 9} neighbors to localize predictions with repeated by location grouped ten-fold cross-validation. To evaluate the information in spectra to facilitate long-term soil monitoring at a plot-level, we conducted 71 model transfers for the NABO sites to induce locally relevant information from the SSL, using the data-driven sample selection method rs-local. Eleven soil properties were estimated with discrimination capacity suitable for screening (R2 > 0.6), out of which total carbon (C), organic C (OC), total N, organic matter content, pH, and clay showed accuracy eligible for accurate diagnostics (R2 > 0.8). Cubist and the spectra estimated total C accurately with RMSE = 0.84 % while the measured range was 0.1–⁠58.3 %, and OC with RMSE = 1.20 % (measured range 0.0–⁠27.3 %). Compared to general estimates of properties from Cubist, local modeling on average reduced the root mean square error of total C per site fourfold. We found that the selected SSL subsets were highly dissimilar in terms of both their spectral input space and the measured values. This suggests that data-driven selection with RS-LOCAL leverages chemical diversity in composition rather than similarity. Our results suggest that mid-IR soil estimates were sufficiently accurate to support many soil applications that require a large volume of input data, such as precision agriculture, soil C accounting and monitoring, and digital soil mapping. This SSL can be updated continuously, for example with samples from deeper profiles and organic soils, so that the measurement of key soil properties becomes even more accurate and efficient in the near future.

scholarly journals Estimation of Secondary Soil Properties by Fusion of Laboratory and On-Line Measured Vis–NIR Spectra

2019 ◽  
Vol 11 (23) ◽  
pp. 2819 ◽  
Author(s):  
Muhammad Abdul Munnaf ◽  
Said Nawar ◽  
Abdul Mounem Mouazen
Keyword(s):  
Soil Properties ◽  
Real Time ◽  
Measurement Accuracy ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Spectral Response ◽  
Nir Spectroscopy ◽  
Accurate Estimation ◽  
Line Measurement ◽  
On Line

Visible and near infrared (vis–NIR) diffuse reflectance spectroscopy has made invaluable contributions to the accurate estimation of soil properties having direct and indirect spectral responses in NIR spectroscopy with measurements made in laboratory, in situ or using on-line (while the sensor is moving) platforms. Measurement accuracies vary with measurement type, for example, accuracy is higher for laboratory than on-line modes. On-line measurement accuracy deteriorates further for secondary (having indirect spectral response) soil properties. Therefore, the aim of this study is to improve on-line measurement accuracy of secondary properties by fusion of laboratory and on-line scanned spectra. Six arable fields were scanned using an on-line sensing platform coupled with a vis–NIR spectrophotometer (CompactSpec by Tec5 Technology for spectroscopy, Germany), with a spectral range of 305–1700 nm. A total of 138 soil samples were collected and used to develop five calibration models: (i) standard, using 100 laboratory scanned samples; (ii) hybrid-1, using 75 laboratory and 25 on-line samples; (iii) hybrid-2, using 50 laboratory and 50 on-line samples; (iv) hybrid-3, using 25 laboratory and 75 on-line samples, and (v) real-time using 100 on-line samples. Partial least squares regression (PLSR) models were developed for soil pH, available potassium (K), magnesium (Mg), calcium (Ca), and sodium (Na) and quality of models were validated using an independent prediction dataset (38 samples). Validation results showed that the standard models with laboratory scanned spectra provided poor to moderate accuracy for on-line prediction, and the hybrid-3 and real-time models provided the best prediction results, although hybrid-2 model with 50% on-line spectra provided equally good results for all properties except for pH and Na. These results suggest that either the real-time model with exclusively on-line spectra or the hybrid model with fusion up to 50% (except for pH and Na) and 75% on-line scanned spectra allows significant improvement of on-line prediction accuracy for secondary soil properties using vis–NIR spectroscopy.

scholarly journals Aeolian nutrient fluxes following wildfire in sagebrush steppe: implications for soil carbon storage

2011 ◽  
Vol 8 (4) ◽  
pp. 8323-8349 ◽  
Author(s):  
N. J. Hasselquist ◽  
M. J. Germino ◽  
J. B. Sankey ◽  
L. J. Ingram ◽  
N. F. Glenn
Keyword(s):  
Biogeochemical Cycling ◽  
Total Carbon ◽  
Sagebrush Steppe ◽  
Nutrient Fluxes ◽  
Aeolian Transport ◽  
Organic C ◽  
Soil C ◽  
N Fluxes ◽  
C And N ◽  
Semi Arid

Abstract. Pulses of aeolian transport following fire can profoundly affect the biogeochemical cycling of nutrients in semi-arid and arid ecosystems. Our objective was to determine horizontal nutrient fluxes during an episodic pulse of aeolian transport that occurred following a wildfire in a semi-arid sagebrush steppe ecosystem in southern Idaho, USA. We also examined how temporal trends in nutrient fluxes were affected by changes in particle sizes of eroded mass as well as nutrient concentrations associated with different particle size classes. In the burned area, total carbon (C) and nitrogen (N) fluxes were as high as 235 g C m−1 d−1 and 19 g N m−1 d−1 during the first few months following fire, whereas C and N fluxes were negligible in an adjacent unburned area throughout the study. Temporal variation in C and N fluxes following fire was largely attributable to the redistribution of saltation-sized particles. Total N and organic C concentrations in the soil surface were significantly lower in the burned relative to the unburned area one year after fire. Our results show how an episodic pulse of aeolian transport following fire can affect the spatial distribution of soil C and N, which, in turn, can have important implications for soil C storage. These findings demonstrate how an ecological disturbance can exacerbate a geomorphic process and highlight the need for further research to better understand the role aeolian transport plays in the biogeochemical cycling of C and N in recently burned landscapes.

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–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 (350–2500 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 R² 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 R² of 0.95. These results are relevant for the INP management plan, and also to similar environments. The good correlation with Vis–NIR techniques can be used for remote sense monitoring, especially in areas with very restricted access such as INP.

scholarly journals Improving In-Situ Estimation of Soil Profile Properties Using a Multi-Sensor Probe

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1011 ◽  
Author(s):  
Xiaoshuai Pei ◽  
Kenneth Sudduth ◽  
Kristen Veum ◽  
Minzan Li
Keyword(s):  
Soil Properties ◽  
Soil Profile ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Chemical Properties ◽  
Estimation Accuracy ◽  
Soil Core ◽  
Least Squares Regression ◽  
Calibration Methods

Optical diffuse reflectance spectroscopy (DRS) has been used for estimating soil physical and chemical properties in the laboratory. In-situ DRS measurements offer the potential for rapid, reliable, non-destructive, and low cost measurement of soil properties in the field. In this study, conducted on two central Missouri fields in 2016, a commercial soil profile instrument, the Veris P4000, acquired visible and near-infrared (VNIR) spectra (343–2222 nm), apparent electrical conductivity (ECa), cone index (CI) penetrometer readings, and depth data, simultaneously to a 1 m depth using a vertical probe. Simultaneously, soil core samples were obtained and soil properties were measured in the laboratory. Soil properties were estimated using VNIR spectra alone and in combination with depth, ECa, and CI (DECS). Estimated soil properties included soil organic carbon (SOC), total nitrogen (TN), moisture, soil texture (clay, silt, and sand), cation exchange capacity (CEC), calcium (Ca), magnesium (Mg), potassium (K), and pH. Multiple preprocessing techniques and calibration methods were applied to the spectral data and evaluated. Calibration methods included partial least squares regression (PLSR), neural networks, regression trees, and random forests. For most soil properties, the best model performance was obtained with the combination of preprocessing with a Gaussian smoothing filter and analysis by PLSR. In addition, DECS improved estimation of silt, sand, CEC, Ca, and Mg over VNIR spectra alone; however, the improvement was more than 5% only for Ca. Finally, differences in estimation accuracy were observed between the two fields despite them having similar soils, with one field demonstrating better results for all soil properties except silt. Overall, this study demonstrates the potential for in-situ estimation of profile soil properties using a multi-sensor approach, and provides suggestions regarding the best combination of sensors, preprocessing, and modeling techniques for in-situ estimation of profile soil properties.

scholarly journals Effects of Subsetting by Carbon Content, Soil Order, and Spectral Classification on Prediction of Soil Total Carbon with Diffuse Reflectance Spectroscopy

2012 ◽  
Vol 2012 ◽  
pp. 1-14 ◽  
Author(s):  
Meryl L. McDowell ◽  
Gregory L. Bruland ◽  
Jonathan L. Deenik ◽  
Sabine Grunwald
Keyword(s):  
Diffuse Reflectance ◽  
Near Infrared ◽  
Prediction Models ◽  
Mean Squared Error ◽  
Diffuse Reflectance Spectroscopy ◽  
Reflectance Spectroscopy ◽  
Total Carbon ◽  
Coefficient Of Determination ◽  
Spectral Classification ◽  
Sample Set

Subsetting of samples is a promising avenue of research for the continued improvement of prediction models for soil properties with diffuse reflectance spectroscopy. This study examined the effects of subsetting by soil total carbon (Ct) content, soil order, and spectral classification withk-means cluster analysis on visible/near-infrared and mid-infrared partial least squares models forCtprediction. Our sample set was composed of various Hawaiian soils from primarily agricultural lands withCtcontents from <1% to 56%. Slight improvements in the coefficient of determination (R2) and other standard model quality parameters were observed in the models for the subset of the high activity clay soil orders compared to the models of the full sample set. The other subset models explored did not exhibit improvement across all parameters. Models created from subsets consisting of only lowCtsamples (e.g.,Ct< 10%) showed improvement in the root mean squared error (RMSE) and percent error of prediction for lowCtsoil samples. These results provide a basis for future study of practical subsetting strategies for soilCtprediction.

scholarly journals Modelling the genesis of equatorial podzols: age and implications for carbon fluxes

2017 ◽  
Vol 14 (9) ◽  
pp. 2429-2440 ◽  
Author(s):  
Cédric Doupoux ◽  
Patricia Merdy ◽  
Célia Régina Montes ◽  
Naoise Nunan ◽  
Adolpho José Melfi ◽  
...  
Keyword(s):  
Organic Matter ◽  
Carbon Fluxes ◽  
Total Carbon ◽  
Organic C ◽  
Perched Water Table ◽  
C Dynamics ◽  
14C Age ◽  
Order Of Magnitude ◽  
Over Time ◽  
Main Carbon

Abstract. Amazonian podzols store huge amounts of carbon and play a key role in transferring organic matter to the Amazon River. In order to better understand their C dynamics, we modelled the formation of representative Amazonian podzol profiles by constraining both total carbon and radiocarbon. We determined the relationships between total carbon and radiocarbon in organic C pools numerically by setting constant C and 14C inputs over time. The model was an effective tool for determining the order of magnitude of the carbon fluxes and the time of genesis of the main carbon-containing horizons, i.e. the topsoil and deep Bh. We performed retrocalculations to take into account the bomb carbon in the young topsoil horizons (calculated apparent 14C age from 62 to 109 years). We modelled four profiles representative of Amazonian podzols, two profiles with an old Bh (calculated apparent 14C age 6.8  ×  103 and 8.4  ×  103 years) and two profiles with a very old Bh (calculated apparent 14C age 23.2  ×  103 and 25.1  ×  103 years). The calculated fluxes from the topsoil to the perched water table indicate that the most waterlogged zones of the podzolized areas are the main source of dissolved organic matter found in the river network. It was necessary to consider two Bh carbon pools to accurately represent the carbon fluxes leaving the Bh as observed in previous studies. We found that the genesis time of the studied soils was necessarily longer than 15  ×  103 and 130  ×  103 years for the two younger and two older Bhs, respectively, and that the genesis time calculated considering the more likely settings runs to around 15  ×  103–25  ×  103 and 150  ×  103–250  ×  103 years, respectively.

scholarly journals Proximal sensing for soil carbon accounting

SOIL ◽  
2018 ◽  
Vol 4 (2) ◽  
pp. 101-122 ◽  
Author(s):  
Jacqueline R. England ◽  
Raphael A. Viscarra Rossel
Keyword(s):  
Bulk Density ◽  
Financial Incentives ◽  
Management Practices ◽  
Near Infrared ◽  
Carbon Accounting ◽  
Soil Organic C ◽  
Proximal Sensing ◽  
Organic C ◽  
Soil C ◽  
Cost Efficient

Abstract. Maintaining or increasing soil organic carbon (C) is vital for securing food production and for mitigating greenhouse gas (GHG) emissions, climate change, and land degradation. Some land management practices in cropping, grazing, horticultural, and mixed farming systems can be used to increase organic C in soil, but to assess their effectiveness, we need accurate and cost-efficient methods for measuring and monitoring the change. To determine the stock of organic C in soil, one requires measurements of soil organic C concentration, bulk density, and gravel content, but using conventional laboratory-based analytical methods is expensive. Our aim here is to review the current state of proximal sensing for the development of new soil C accounting methods for emissions reporting and in emissions reduction schemes. We evaluated sensing techniques in terms of their rapidity, cost, accuracy, safety, readiness, and their state of development. The most suitable method for measuring soil organic C concentrations appears to be visible–near-infrared (vis–NIR) spectroscopy and, for bulk density, active gamma-ray attenuation. Sensors for measuring gravel have not been developed, but an interim solution with rapid wet sieving and automated measurement appears useful. Field-deployable, multi-sensor systems are needed for cost-efficient soil C accounting. Proximal sensing can be used for soil organic C accounting, but the methods need to be standardized and procedural guidelines need to be developed to ensure proficient measurement and accurate reporting and verification. These are particularly important if the schemes use financial incentives for landholders to adopt management practices to sequester soil organic C. We list and discuss requirements for developing new soil C accounting methods based on proximal sensing, including requirements for recording, verification, and auditing.

Sign in / Sign up

Export Citation Format

Share Document