Predicting Soil Organic Matter, Available Nitrogen, Available Phosphorus and Available Potassium in a Black Soil Using a Nearby Hyperspectral Sensor System.

Black soils, which play an important role in agricultural production and food security, are well known for their relatively high content of soil organic matter (SOM). SOM has a significant impact on the sustainability of farmland and provides nutrients for plants. Hyperspectral imaging (HSI) in the visible and near-infrared region has shown the potential to detect soil nutrient levels in the laboratory. However, using portable spectrometers directly in the field remains challenging due to variations in soil moisture (SM). The current study used spectral data captured by a handheld spectrometer outdoors to predict SOM, available nitrogen (AN), available phosphorus (AP) and available potassium (AK) with different SM levels. Partial least squares regression (PLSR) models were established to compare the predictive performance of air-dried soil samples with SMs around 20%, 30% and 40%. The results showed that the model established using dry sample data had the best performance (RMSE = 4.47 g/kg) for the prediction of SOM, followed by AN (RMSE = 20.92 mg/kg) and AK (RMSE = 22.67 mg/kg). The AP was better predicted by the model based on 30% SM (RMSE = 8.04 mg/kg). In general, model performance deteriorated with an increase in SM, except for the case of AP. Feature wavelengths for predicting four kinds of soil properties were recommended based on variable importance in the projection (VIP), which offered useful guidance for the development of portable hyperspectral sensors based on discrete wavebands to reduce cost and save time for on-site data collection.

Improved Field-Based Soybean Seed Counting and Localization with Feature Level Considered.

Developing automated soybean seed counting tools will help automate yield prediction before harvesting and improving selection efficiency in breeding programs. An integrated approach for counting and localization is ideal for subsequent analysis. The traditional method of object counting is labor-intensive and error-prone and has low localization accuracy. To quantify soybean seed directly rather than sequentially, we propose a P2PNet-Soy method. Several strategies were considered to adjust the architecture and subsequent postprocessing to maximize model performance in seed counting and localization. First, unsupervised clustering was applied to merge closely located overcounts. Second, low-level features were included with high-level features to provide more information. Third, atrous convolution with different kernel sizes was applied to low- and high-level features to extract scale-invariant features to factor in soybean size variation. Fourth, channel and spatial attention effectively separated the foreground and background for easier soybean seed counting and localization. At last, the input image was added to these extracted features to improve model performance. Using 24 soybean accessions as experimental materials, we trained the model on field images of individual soybean plants obtained from one side and tested them on images obtained from the opposite side, with all the above strategies. The superiority of the proposed P2PNet-Soy in soybean seed counting and localization over the original P2PNet was confirmed by a reduction in the value of the mean absolute error, from 105.55 to 12.94. Furthermore, the trained model worked effectively on images obtained directly from the field without background interference.

Root traits of European Vicia faba cultivars-Using machine learning to explore adaptations to agroclimatic conditions.

Faba bean (Vicia faba L.) is an important source of protein, but breeding for increased yield stability and stress tolerance is hampered by the scarcity of phenotyping information. Because comparisons of cultivars adapted to different agroclimatic zones improve our understanding of stress tolerance mechanisms, the root architecture and morphology of 16 European faba bean cultivars were studied at maturity. Different machine learning (ML) approaches were tested in their usefulness to analyse trait variations between cultivars. A supervised, that is, hypothesis-driven, ML approach revealed that cultivars from Portugal feature greater and coarser but less frequent lateral roots at the top of the taproot, potentially enhancing water uptake from deeper soil horizons. Unsupervised clustering revealed that trait differences between northern and southern cultivars are not predominant but that two cultivar groups, independently from major and minor types, differ largely in overall root system size. Methodological guidelines on how to use powerful ML methods such as random forest models for enhancing the phenotypical exploration of plants are given.

Root architecture simulation improves the inference from seedling root phenotyping towards mature root systems.

Root phenotyping provides trait information for plant breeding. A shortcoming of high-throughput root phenotyping is the limitation to seedling plants and failure to make inferences on mature root systems. We suggest root system architecture (RSA) models to predict mature root traits and overcome the inference problem. Sixteen pea genotypes were phenotyped in (i) seedling (Petri dishes) and (ii) mature (sand-filled columns) root phenotyping platforms. The RSA model RootBox was parameterized with seedling traits to simulate the fully developed root systems. Measured and modelled root length, first-order lateral number, and root distribution were compared to determine key traits for model-based prediction. No direct relationship in root traits (tap, lateral length, interbranch distance) was evident between phenotyping systems. RootBox significantly improved the inference over phenotyping platforms. Seedling plant tap and lateral root elongation rates and interbranch distance were sufficient model parameters to predict genotype ranking in total root length with an RSpearman of 0.83. Parameterization including uneven lateral spacing via a scaling function substantially improved the prediction of architectures underlying the differently sized root systems. We conclude that RSA models can solve the inference problem of seedling root phenotyping. RSA models should be included in the phenotyping pipeline to provide reliable information on mature root systems to breeding research.

Paclobutrazol induces tolerance in tomato to deficit irrigation through diversified effects on plant morphology, physiology and metabolism.

Dwindling water resources combined with meeting the demands for food security require maximizing water use efficiency (WUE) both in rainfed and irrigated agriculture. In this regard, deficit irrigation (DI), defined as the administration of water below full crop-water requirements (evapotranspiration), is a valuable practice to contain irrigation water use. In this study, the mechanism of paclobutrazol (Pbz)-mediated improvement in tolerance to water deficit in tomato was thoroughly investigated. Tomato plants were subjected to normal irrigated and deficit irrigated conditions plus Pbz application (0.8 and 1.6 ppm). A comprehensive morpho-physiological, metabolomics and molecular analysis was undertaken. Findings revealed that Pbz application reduced plant height, improved stem diameter and leaf number, altered root architecture, enhanced photosynthetic rates and WUE of tomato plants under deficit irrigation. Pbz differentially induced expression of genes and accumulation of metabolites of the tricarboxylic acid (TCA) cycle, γ-aminobutyric acid (GABA-shunt pathway), glutathione ascorbate (GSH-ASC)-cycle, cell wall and sugar metabolism, abscisic acid (ABA), spermidine (Spd) content and expression of an aquaporin (AP) protein under deficit irrigation. Our results suggest that Pbz application could significantly improve tolerance in tomato plants under limited water availability through selective changes in morpho-physiology and induction of stress-related molecular processes.

Phenotyping: Using Machine Learning for Improved Pairwise Genotype Classification Based on Root Traits.

Phenotyping local crop cultivars is becoming more and more important, as they are an important genetic source for breeding - especially in regard to inherent root system architectures. Machine learning algorithms are promising tools to assist in the analysis of complex data sets; novel approaches are need to apply them on root phenotyping data of mature plants. A greenhouse experiment was conducted in large, sand-filled columns to differentiate 16 European Pisum sativum cultivars based on 36 manually derived root traits. Through combining random forest and support vector machine models, machine learning algorithms were successfully used for unbiased identification of most distinguishing root traits and subsequent pairwise cultivar differentiation. Up to 86% of pea cultivar pairs could be distinguished based on top five important root traits (Timp5) - Timp5 differed widely between cultivar pairs. Selecting top important root traits (Timp) provided a significant improved classification compared to using all available traits or randomly selected trait sets. The most frequent Timp of mature pea cultivars was total surface area of lateral roots originating from tap root segments at 0-5 cm depth. The high classification rate implies that culturing did not lead to a major loss of variability in root system architecture in the studied pea cultivars. Our results illustrate the potential of machine learning approaches for unbiased (root) trait selection and cultivar classification based on rather small, complex phenotypic data sets derived from pot experiments. Powerful statistical approaches are essential to make use of the increasing amount of (root) phenotyping information, integrating the complex trait sets describing crop cultivars.