A framework for optimizing environmental covariates to support model interpretability in digital soil mapping

Geoderma, Journal Year: 2024, Volume and Issue: 445, P. 116873 - 116873

Published: April 4, 2024

A common practice in digital soil mapping (DSM) is to incorporate many environmental covariates into a machine-learning algorithm predict the spatial patterns of attributes. Variance inflation factor (VIF), principal component analysis (PCA), and recursive feature elimination (RFE) are three statistical methods that can be used reduce number covariates. This study aims 1) compare VIF PCA approaches; 2) identify an approach determine minimum DSM ensure model parsimony using RFE after VIF; 3) examine interpret impact on variability predicted properties. The area was province British Columbia (BC), Canada. legacy data for four properties make maps: organic carbon (SOC%), pH, clay%, coarse fragment (CF%). Seven models were made each property influence validation results by different produced various results. showed could reduced from 70 4 12 with only little or no difference concordance correlation coefficient (CCC) CCC pH 7 both 0.74, other properties, this negligible. obtained performance reducing not as effective when VIF. Moreover, related precipitation most important modeling SOC%, clay%. Topographic influential CF%. emphasizes potential benefits combining reduction achieve optimal outcomes generate parsimonious interpretable models.

Language: Английский

---

Pedotransfer Functions for Soil Protein Based on Random Forest Modeling for Routine Soil Health Analysis

Communications in Soil Science and Plant Analysis, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 13

Published: Jan. 18, 2025

Autoclaved-citrate extractable soil protein (ACE protein, hereafter referred as "soil protein") is a novel biological health indicator that can indirectly capture soil's capacity to supply nitrogen (N) but relatively expensive assess. To explore cost saving options, dataset of 4,171 samples with texture, total carbon (C) and N, carbon-to-nitrogen ratio (C/N), permanganate-oxidizable (POXC), pH, magnesium (Mg) iron (Fe), was used develop three pedotransfer functions for protein. These included full random forest (RF) model utilizing all variables, reduced RF multiple linear regression employing subset the variables. Models were validated using US North American Project Evaluate Soil Health Measurements contained 1,406 samples. The root mean square error (RMSE) by 41.7 53.4% compared models, respectively. Total C more important variable in than N. Additionally, POXC, sand, clay, Mg Fe found be model. sensitive management at 36 57 long-term experiments. able replicate 92% those significant effects on new function improve prediction traditional techniques reduce comprehensive assessment.

Language: Английский

---

Evaluating the effect of biochar rate and combination with fertilizer on the dynamics of soil nitrogen supply in tea plantation

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 24, 2025

Tea plantations commonly receive substantial quantities of nitrogen (N) fertilizer, with potential for considerable N loss to occur. This study assessed retention in acidic tea plantation soil and examined how different biochar application rates fertilizer combinations affect dynamics, highlighting the importance innovative technologies monitor enhance supply management. research adopted a modified 2-week aerobic incubation ion-exchange membrane (IEM) techniques evaluate following early-summer top-dressing as influenced by various combinations. We quantified amount mineralized soils during summer. Our results show that enhances not increasing mineralization directly but improving mineral retention. Notably, threshold effect was identified at 20–30 tonnes ha−1. The window maximizing effectiveness inorganic fertilizers applied summer months could only be 2–4 weeks. use biochar-based organic can this period enhancing availability soil. Measuring via incubations exposure using IEM technology effectively elucidated dynamics period.

Language: Английский

---

Integrating multi-year crop inventories as a proxy for soil management within a digital soil mapping framework for predicting nitrogen indices

Geoderma, Journal Year: 2024, Volume and Issue: 448, P. 116944 - 116944

Published: June 25, 2024

For the international digital soil mapping (DSM) community, adequate spatial estimates of nitrogen (N) mineralization have yet to be generated. This is due, in part, an inability capture critical N controls at regional and provincial scales. While influence climate, vegetation, relief are accessible predictors DSM, effect management known for its important on dynamics, but has hitherto been elusive mappers. purpose producing maps inform fertilizer management, intention this study was determine importance novel crop frequency layers, as a proxy through development scale DSMs total (TN), biological availability (BNA) estimate over growing season (GSN) calculated from TN BNA results. Crop covariates were developed that estimated particular type planted 10-year period, thus capturing cropping system tillage intensity. results 27% higher using layers support vector machine learner, with Lin's concordance correlation coefficient (concordance) 0.45. predictions increased by 24% stochastic gradient boosting learner final GSN showed least improvement (6%) resulted highest (0.47) learner. The stable pool, represented TN, climate importance; whereas, labile based measures, best predicted controlled organism covariates. successful inclusion into indicated number times forages potatoes period greatest importance. As intensity most pronounced potatoes, contribute biomass building organic matter levels, increasing years had positive pools.

Language: Английский

---

Filling the gaps in soil data: A multi-model framework for addressing data gaps using pedotransfer functions and machine-learning with uncertainty estimates to estimate bulk density

CATENA, Journal Year: 2024, Volume and Issue: 245, P. 108310 - 108310

Published: Aug. 23, 2024

Language: Английский

---

Effect of biochar and its combined fertilizers on the dynamics of soil nitrogen supply in tea plantation

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 22, 2024

Background and Aims: Tea plantations are frequently given substantial quantities of nitrogen fertilizers. However, there is the potential for considerable loss to occur. This study assesses retention acidic tea plantation’s soil role biochar in improving dynamics, highlighting need innovative technologies streamline enhance supply management. Methods: Adopting a modified two-week aerobic incubation ion-exchange membrane technology, this research offers novel approach evaluate monitor dynamics plantation following early-summer supplementary fertilization. Results: The revealed that surface had ability provide 48 mg N·kg^-1 as inorganic 130 days. utilization small amount (10 t·ha^-1) no impact on soil's effective availability. Nonetheless, application at rates 20 30 t·ha^-1 resulted significant enhancement availability measured using ion exchange membranes, with an increase 65%–81%. Furthermore, biochar-based organic fertilizers, when used appropriate rates, has soil, thereby increasing its effectiveness. Conclusion: study's findings underscore efficacy employed methodologies capturing nuanced soils. use technology proven elucidating significantly improve dynamics.

Language: Английский

---