Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo
This near-infrared spectral dataset consists of 2,106 diverse mineral soil samples scanned, on average, on six different units of the same low-cost commercially available handheld spectrophotometer. Most soil samples were selected from the USDA NRCS National Soil Survey Center-Kellogg Soil Survey La...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Data in Brief |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352340924011910 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576509374627840 |
|---|---|
| author | Colleen Partida Jose Lucas Safanelli Sadia Mannan Mitu Mohammad Omar Faruk Murad Yufeng Ge Richard Ferguson Keith Shepherd Jonathan Sanderman |
| author_facet | Colleen Partida Jose Lucas Safanelli Sadia Mannan Mitu Mohammad Omar Faruk Murad Yufeng Ge Richard Ferguson Keith Shepherd Jonathan Sanderman |
| author_sort | Colleen Partida |
| collection | DOAJ |
| description | This near-infrared spectral dataset consists of 2,106 diverse mineral soil samples scanned, on average, on six different units of the same low-cost commercially available handheld spectrophotometer. Most soil samples were selected from the USDA NRCS National Soil Survey Center-Kellogg Soil Survey Laboratory (NSSC-KSSL) soil archives to represent the diversity of mineral soils (0–30 cm) found in the United States, while 90 samples were selected from Ghana, Kenya, and Nigeria to represent available African soils in the same archive. All scanning was performed on dried and sieved (<2 mm) soil samples. Machine learning predictive models were developed for soil organic carbon (SOC), pH, bulk density (BD), carbonate (CaCO3), exchangeable potassium (Ex. K), sand, silt, and clay content from their spectra in the R programming language using most of this dataset (1,976 US soils) and are included in this data release. Two model types, Cubist and partial least squares regression (PLSR) were developed using two strategies: (1) using an average of the spectral scans across devices for each sample and, (2) using the replicate spectral scans across devices for each sample. We present the internal performance of these models here. The dry spectra and Cubist models for these soil properties are available for download from 10.5281/zenodo.7586621. An example of detailed code used to produce these models is hosted at the Open Soil Spectral Library, a free service of the Soil Spectroscopy for the Global Good Network (soilspectroscopy.org), enabling broad use of these data for multiple soil monitoring applications. |
| format | Article |
| id | doaj-art-d39b0410d7404c4dbd410e96d281ce63 |
| institution | Kabale University |
| issn | 2352-3409 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Data in Brief |
| spelling | doaj-art-d39b0410d7404c4dbd410e96d281ce632025-01-31T05:11:34ZengElsevierData in Brief2352-34092025-02-0158111229Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodoColleen Partida0Jose Lucas Safanelli1Sadia Mannan Mitu2Mohammad Omar Faruk Murad3Yufeng Ge4Richard Ferguson5Keith Shepherd6Jonathan Sanderman7Woodwell Climate Research Center, 149 Woods Hole Rd., Falmouth, MA, 02540, United StatesWoodwell Climate Research Center, 149 Woods Hole Rd., Falmouth, MA, 02540, United StatesDepartment of Biological Systems Engineering, University of Nebraska-Lincoln, E Campus Mall, Lincoln, NE, 68583, United StatesDepartment of Biological Systems Engineering, University of Nebraska-Lincoln, E Campus Mall, Lincoln, NE, 68583, United StatesDepartment of Biological Systems Engineering, University of Nebraska-Lincoln, E Campus Mall, Lincoln, NE, 68583, United StatesUSDA, Natural Resources Conservation Service (NRCS), National Soil Survey Center (NSSC), Kellogg Soil Survey Laboratory (KSSL), 1121 Lincoln Mall, Lincoln, NE, 68508, United StatesInnovative Solutions for Decision Agriculture (iSDA), Rothamsted Campus, West Common, Harpendedn AL5 2JQ, UKWoodwell Climate Research Center, 149 Woods Hole Rd., Falmouth, MA, 02540, United States; Corresponding author.This near-infrared spectral dataset consists of 2,106 diverse mineral soil samples scanned, on average, on six different units of the same low-cost commercially available handheld spectrophotometer. Most soil samples were selected from the USDA NRCS National Soil Survey Center-Kellogg Soil Survey Laboratory (NSSC-KSSL) soil archives to represent the diversity of mineral soils (0–30 cm) found in the United States, while 90 samples were selected from Ghana, Kenya, and Nigeria to represent available African soils in the same archive. All scanning was performed on dried and sieved (<2 mm) soil samples. Machine learning predictive models were developed for soil organic carbon (SOC), pH, bulk density (BD), carbonate (CaCO3), exchangeable potassium (Ex. K), sand, silt, and clay content from their spectra in the R programming language using most of this dataset (1,976 US soils) and are included in this data release. Two model types, Cubist and partial least squares regression (PLSR) were developed using two strategies: (1) using an average of the spectral scans across devices for each sample and, (2) using the replicate spectral scans across devices for each sample. We present the internal performance of these models here. The dry spectra and Cubist models for these soil properties are available for download from 10.5281/zenodo.7586621. An example of detailed code used to produce these models is hosted at the Open Soil Spectral Library, a free service of the Soil Spectroscopy for the Global Good Network (soilspectroscopy.org), enabling broad use of these data for multiple soil monitoring applications.http://www.sciencedirect.com/science/article/pii/S2352340924011910Soil spectroscopySoil organic carbonPedometricsChemometricsSoil analysis |
| spellingShingle | Colleen Partida Jose Lucas Safanelli Sadia Mannan Mitu Mohammad Omar Faruk Murad Yufeng Ge Richard Ferguson Keith Shepherd Jonathan Sanderman Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo Data in Brief Soil spectroscopy Soil organic carbon Pedometrics Chemometrics Soil analysis |
| title | Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo |
| title_full | Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo |
| title_fullStr | Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo |
| title_full_unstemmed | Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo |
| title_short | Building a near-infrared (NIR) soil spectral dataset and predictive machine learning models using a handheld NIR spectrophotometerZenodo |
| title_sort | building a near infrared nir soil spectral dataset and predictive machine learning models using a handheld nir spectrophotometerzenodo |
| topic | Soil spectroscopy Soil organic carbon Pedometrics Chemometrics Soil analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2352340924011910 |
| work_keys_str_mv | AT colleenpartida buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT joselucassafanelli buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT sadiamannanmitu buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT mohammadomarfarukmurad buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT yufengge buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT richardferguson buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT keithshepherd buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo AT jonathansanderman buildinganearinfrarednirsoilspectraldatasetandpredictivemachinelearningmodelsusingahandheldnirspectrophotometerzenodo |