Parent, S.-E. | bioRxiv Science

bioRxiv2020

Machine learning prediction of particle-size distribution from infrared spectra, methodologies and soil features

Accuracy of infrared (IR) models to measure soil particle-size distribution (PSD) depends on soil preparation, methodology (sedimentation, laser), settling times and relevant soil features. Compositional soil data may require log ratio (ilr) transformation to avoid numerical biases. Machine learning can relate numerous independent variables that may impact on NIR spectra to assess particle-size distribution. Our objective was to reach high IRS prediction accuracy across a large range of PSD methods and soil properties. A total of 1298 soil samples from eastern Canada were IR-scanned. Spectra were processed by Stochastic Gradient Boosting (SGB) to predict sand, silt, clay and carbon. Slope and intercept of the log-log relationships between settling time and suspension density function (SDF) (R2 = 0.84-0.92) performed similarly to NIR spectra using either ilr-transformed (R2 = 0.81-0.93) or raw percentages (R2 = 0.76-0.94). Settling times of 0.67-min and 2-h were the most accurate for NIR predictions (R2 = 0.49-0.79). The NIR prediction of sand sieving method (R2 = 0.66) was more accurate than Bouyoucos (R2 = 0.53). The NIR 2X gain was less accurate (R2 = 0.69-0.92) than 4X (R2 = 0.87-0.95). The MIR (R2 = 0.45-0.80) performed better than NIR (R2 = 0.40-0.71) spectra. Adding soil carbon, reconstituted bulk density, pH, red-green-blue color, oxalate and Mehlich3 extracts returned R2 value of 0.86-0.91 for texture prediction. In addition to slope and intercept of the SDF, 4X gain, method and pre-treatment classes, soil carbon and color appeared to be promising features for routine SGB-processed NIR particle-size analysis. Soil Classification (Soil Taxonomy): Inceptisols, Spodosols

ecology↗

bioRxiv2020

Site-specific machine learning predictive fertilization models for potato crops in Eastern Canada.

1Statistical modeling is commonly used to relate the performance of potato (Solanum tuberosum L.) to fertilizer requirements. Prescribing optimal nutrient doses is challenging because of the involvement of many variables including weather, soils, land management, genotypes, and severity of pests and diseases. Where sufficient data are available, machine learning algorithms can be used to predict crop performance. The objective of this study was to predict tuber yield and quality (size and specific gravity) as impacted by nitrogen, phosphorus and potassium fertilization as well as weather, soils and land management variables. We exploited a data set of 273 field experiments conducted from 1979 to 2017 in Quebec (Canada). We developed, evaluated and compared predictions from a hierarchical Mitscherlich model, k-nearest neighbors, random forest, neuronal networks and Gaussian processes. Machine learning models returned R2 values of 0.49-0.59 for tuber marketable yield prediction, which were higher than the Mitscherlich model R2 (0.37). The models were more likely to predict medium-size tubers (R2 = 0.60-0.69) and tuber specific gravity (R2 = 0.58-0.67) than large-size tubers (R2 = 0.55-0.64) and marketable yield. Response surfaces from the Mitscherlich model, neural networks and Gaussian processes returned smooth responses that agreed more with actual evidence than discontinuous curves derived from k-nearest neighbors and random forest models. When marginalized to obtain optimal dosages from dose-response surfaces given constant weather, soil and land management conditions, some disagreements occurred between models. Due to their built-in ability to develop recommendations within a probabilistic risk-assessment framework, Gaussian processes stood out as the most promising algorithm to support decisions that minimize economic or agronomic risks.

systems biology↗