Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement

PLoS ONE, Год журнала: 2025, Номер 20(1), С. e0296545 - e0296545

Опубликована: Янв. 13, 2025

Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, bottleneck its more widespread adoption the need establishing large reference datasets training machine learning (ML) models, which called spectral libraries (SSLs). Similarly, prediction capacity of new samples also subject number diversity types conditions represented in SSLs. To help bridge this gap enable hundreds stakeholders collect affordable data by leveraging centralized open resource, Spectroscopy Global Good initiative has created Open Spectral Library (OSSL). In paper, we describe procedures collecting harmonizing several SSLs incorporated into OSSL, followed exploratory analysis predictive modeling. The results 10-fold cross-validation with refitting show that, general, mid-infrared (MIR)-based models significantly accurate than visible near-infrared (VisNIR) or (NIR) models. From independent model evaluation, found Cubist comes out as best-performing ML algorithm calibration delivery reliable outputs (prediction uncertainty representation flag). Although many well predicted, total sulfur, extractable sodium, electrical conductivity performed poorly all regions, some other nutrients physical performing one two regions (VisNIR NIR). Hence, use based solely on variations limitations. This study presents discusses resources were developed from aspects opening data, current limitations, future development. With genuinely science project, hope OSSL becomes driver community accelerate pace scientific discovery innovation.

Язык: Английский

---

Global 1 km land surface parameters for kilometer-scale Earth system modeling

Earth system science data, Год журнала: 2024, Номер 16(4), С. 2007 - 2032

Опубликована: Апрель 29, 2024

Abstract. Earth system models (ESMs) are progressively advancing towards the kilometer scale (“k-scale”). However, surface parameters for land (LSMs) within ESMs running at k-scale typically derived from coarse-resolution and outdated datasets. This study aims to develop a new set of global with resolution 1 km multiple years 2001 2020, utilizing latest most accurate available Specifically, datasets consist related use cover, vegetation, soil, topography. Differences between newly developed conventional emphasize their potential higher accuracy due incorporation advanced data sources. To demonstrate capability these parameters, we conducted simulations using E3SM Land Model version 2 (ELM2) over contiguous United States. Our results that contribute significant spatial heterogeneity in ELM2 soil moisture, latent heat, emitted longwave radiation, absorbed shortwave radiation. On average, about 31 % 54 information is lost by upscaling 12 resolution. Using eXplainable Machine Learning (XML) methods, influential factors driving variability loss were identified, highlighting substantial impact various as well mean climate conditions. The comparison against four benchmark indicates ELM generally performs simulating moisture energy fluxes. tailored meet emerging needs LSM ESM modeling implications our understanding water, carbon, cycles under change. publicly https://doi.org/10.5281/zenodo.10815170 (Li et al., 2024).

Язык: Английский

---

Satellite-enabled enviromics to enhance crop improvement

Molecular Plant, Год журнала: 2024, Номер 17(6), С. 848 - 866

Опубликована: Апрель 17, 2024

Enviromics refers to the characterization of micro- and macroenvironments based on large-scale environmental datasets. By providing genotypic recommendations with predictive extrapolation at a site-specific level, enviromics could inform plant breeding decisions across varying conditions anticipate productivity in changing climate. Enviromics-based integration statistics, envirotyping (i.e., determining factors), remote sensing help unravel complex interplay genetics, environment, management. To support this goal, exhaustive generate precise profiles would significantly improve predictions genotype performance genetic gain crops. Already, informatics management platforms aggregate diverse datasets obtained using optical, thermal, radar, light detection ranging (LiDAR)sensors that capture detailed information about vegetation, surface structure, terrain. This wealth information, coupled freely available climate data, fuels innovative research. While holds immense potential for breeding, few obstacles remain, such as need (1) integrative methodologies systematically collect field data scale expand observations landscape satellite data; (2) state-of-the-art AI models integration, simulation, prediction; (3) cyberinfrastructure processing big scales seamless interfaces deliver forecasts stakeholders; (4) collaboration sharing among farmers, breeders, physiologists, geoinformatics experts, programmers research institutions. Overcoming these challenges is essential leveraging full captured by satellites transform 21st century agriculture crop improvement through enviromics.

Язык: Английский

---

Vital for Sustainable Agriculture: Pedological Knowledge and Mapping

European Journal of Soil Science, Год журнала: 2025, Номер 76(1)

Опубликована: Янв. 1, 2025

ABSTRACT Over the past 60 years, efforts to enhance agricultural productivity have mainly focussed on optimising strategies such as use of inorganic fertilisers, advancements in microbiology and improved water management practices. Here, we emphasise critical role pedology a foundation soil long‐term sustainability. We will demonstrate how overlooking intrinsic properties soils can result detrimental effects overall Communication between academia, extension experts, consultants farmers often results an overemphasis surface layer, for example, 20 40 cm, neglecting functions that occur at depth. Soil health regenerative agriculture must be coupled with understanding dynamic system. find pedological knowledge digital mapping technologies are underused achieving sustainable agriculture. By bridging gap emerging technologies, provide land users tools needed make informed decisions, ensuring their practices not only increase production but also preserve future generations.

Язык: Английский

---

Soil health in Latin America and the Caribbean

Communications Earth & Environment, Год журнала: 2025, Номер 6(1)

Опубликована: Фев. 24, 2025

Язык: Английский

---

Soil organic carbon mapping utilizing convolutional neural networks and Earth observation data, a case study in Bavaria state Germany

Geoderma, Год журнала: 2024, Номер 444, С. 116867 - 116867

Опубликована: Март 28, 2024

The Copernicus Sentinel-2 multispectral imagery data may be aggregated to extract large-scale, bare soil, reflectance composites, which enable soil mapping applications. In this paper, approach was tested in the German federal state of Bavaria, provide estimations for organic carbon (SOC). Different temporal ranges were considered generation including multi-annual and seasonal ranges. A novel multi-channel convolutional neural network (CNN) is proposed. By leveraging advantages deep learning techniques, it utilizes complementary information from different spectral pre-treatment techniques. SOC predictions indicated little dissimilarity amongst with best performance attained six-year composite containing only spring months (RMSE = 12.03 g C · kg−1, R2 0.64, RPIQ 0.89). It has been demonstrated that these outcomes outperform other well-known machine An ablation analysis accordingly performed evaluate interplay CNN's components disentangle each aspect proposed framework. Finally, a DUal inPut LearnIng architecture, named DUPLICITE, proposed, concatenates features derived CNN mentioned earlier, as well topographical environmental covariates through an artificial (ANN) exploit their complementarity. improvement overall prediction 11.60 gC 0.67, 0.92).

Язык: Английский

---

Pixel-by-Pixel Analysis of Soil and Leaf Coverage in Purslane: A CIELAB Approach

Agricultural Sciences, Год журнала: 2025, Номер 16(02), С. 227 - 239

Опубликована: Янв. 1, 2025

Язык: Английский

---

A global soil spectral grid based on space sensing

The Science of The Total Environment, Год журнала: 2025, Номер 968, С. 178791 - 178791

Опубликована: Фев. 20, 2025

Язык: Английский

---

Decoding Soil Color: Origins, Influences, and Methods of Analysis

AgriEngineering, Год журнала: 2025, Номер 7(3), С. 58 - 58

Опубликована: Фев. 25, 2025

Soil color serves as a critical indicator of its properties and conditions. It is shaped by complex interplay mineral organic matter content, moisture levels, other environmental variables. Additionally, human activities such land-use changes intensive agricultural practices can profoundly alter soil color. color, driven the presence matter, plays crucial role in understanding fertility. Its strong correlation with carbon content makes it valuable parameter for assessing quality practices. A variety techniques have been developed to measure ranging from traditional Munsell matching modern meters. Digital image colorimetry enables rapid on-site assessments but conditions water lighting should be considered. Spectroscopic methods, particularly diffuse reflectance spectroscopy, pave way more reliable accurate composition analysis. Advances remote sensing computational methods are combined explore intricate relationships between factors. Such an integrated approach not only enhances scalability also leads insights actionable strategies management sustainable agriculture.

Язык: Английский

---

Time series of Landsat-based bimonthly and annual spectral indices for continental Europe for 2000–2022

Earth system science data, Год журнала: 2025, Номер 17(2), С. 741 - 772

Опубликована: Фев. 26, 2025

Abstract. The production and evaluation of the analysis-ready cloud-optimized (ARCO) data cube for continental Europe (including Ukraine, UK, Türkiye), derived from Landsat dataset version 2 (ARD V2) produced by Global Land Analysis Discovery (GLAD) team covering period 2000 to 2022, is described. consists 17 TB at a 30 m resolution includes bimonthly, annual, long-term spectral indices on various thematic topics, including surface reflectance bands, normalized difference vegetation index (NDVI), soil adjusted (SAVI), fraction absorbed photosynthetically active radiation (FAPAR), snow (NDSI), water (NDWI), tillage (NDTI), minimum (minNDTI), bare (BSF), number seasons (NOS), crop duration ratio (CDR). was developed with intention provide comprehensive feature space environmental modeling mapping. quality time series assessed (1) assessing accuracy gap-filled bimonthly artificially created gaps; (2) visual examination artifacts inconsistencies; (3) plausibility checks ground survey data; (4) predictive tests, examples organic carbon (SOC) land cover (LC) classification. reconstruction demonstrates high accuracy, root mean squared error (RMSE) smaller than 0.05, R2 higher 0.6, across all bands. indicates that product complete consistent, except winter periods in northern latitudes high-altitude areas, where cloud density introduce significant gaps hence many remain. check further shows logically statistically capture processes. BSF showed strong negative correlation (−0.73) coverage data, while minNDTI had moderate positive (0.57) Eurostat practice data. detailed temporal characteristics provided different tiers predictors this proved be important both regression LC classification experiments based 60 723 LUCAS observations: (tier 4) were particularly valuable mapping SOC LC, coming out top variable importance assessment. Crop-specific (NOS CDR) limited value tested applications, possibly due noise or insufficient quantification methods. made available https://doi.org/10.5281/zenodo.10776891 (Tian et al., 2024) under CC-BY license will continuously updated.

Язык: Английский

---