Digital mapping of the soil available water capacity: tool for the resilience of agricultural systems to climate change.

Soil available water capacity (AWC) is a key function for human survival and well-being. However, its direct measurement is laborious and spatial interpretation is complex. Digital soil mapping (DSM) techniques emerge as an alternative to spatial modeling of soil properties. DSM techniques commonly apply machine learning (ML) models, with a high level of complexity. In this context, we aimed to perform a digital mapping of soil AWC and interpret the results of the Random Forest (RF) algorithm and, in a case study, to show that digital AWC maps can support agricultural planning in response to the local effects of climate change. To do so, we divided this research into two approaches: In the first approach, we showed a DSM using 1857 sample points in a southeastern region of Brazil with laboratory-determined soil attributes, together with a pedotransfer function (PTF), remote sensing and DSM techniques. In the second approach, the constructed AWC digital soil map and weather station data were used to calculate climatological soil water balances for the periods between 1917-1946 and 1991-2020. The result showed the selection of covariates using Shapley values as a criterion contributed to the parsimony of the model, obtaining goodness-of-fit metrics of R2 0.72, RMSE 16.72 mm m-1, CCC 0.83, and Bias of 0.53 over the validation set. The highest contributing covariates for soil AWC prediction were the Landsat multitemporal images with bare soil pixels, mean diurnal, and annual temperature range. Under the current climate conditions, soil available water content (AW) increased during the dry period (April to August). May had the highest increase in AW (∼17 mm m-1) and decrease in September (∼14 mm m-1). The used methodology provides support for AWC modeling at 30 m resolution, as well as insight into the adaptation of crop growth periods to the effects of climate change.

Machine Learning for Seed Quality Classification: An Advanced Approach Using Merger Data from FT-NIR Spectroscopy and X-ray Imaging.

Optical sensors combined with machine learning algorithms have led to significant advances in seed science. These advances have facilitated the development of robust approaches, providing decision-making support in the seed industry related to the marketing of seed lots. In this study, a novel approach for seed quality classification is presented. We developed classifier models using Fourier transform near-infrared (FT-NIR) spectroscopy and X-ray imaging techniques to predict seed germination and vigor. A forage grass (Urochloa brizantha) was used as a model species. FT-NIR spectroscopy data and radiographic images were obtained from individual seeds, and the models were created based on the following algorithms: linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), random forest (RF), naive Bayes (NB), and support vector machine with radial basis (SVM-r) kernel. In the germination prediction, the models individually reached an accuracy of 82% using FT-NIR data, and 90% using X-ray data. For seed vigor, the models achieved 61% and 68% accuracy using FT-NIR and X-ray data, respectively. Combining the FT-NIR and X-ray data, the performance of the classification model reached an accuracy of 85% to predict germination, and 62% for seed vigor. Overall, the models developed using both NIR spectra and X-ray imaging data in machine learning algorithms are efficient in quickly, non-destructively, and accurately identifying the capacity of seed to germinate. The use of X-ray data and the LDA algorithm showed great potential to be used as a viable alternative to assist in the quality classification of U. brizantha seeds.