Search

Abstract Background Restricting transpiration under high vapor pressure deficit (VPD) is a promising water-saving trait for drought adaptation. However, it is often measured under controlled conditions and at very low throughput, unsuitable for breeding. A few high-throughput phenotyping (HTP) studies exist, and have considered only maximum transpiration rate in analyzing genotypic differences in this trait. Further, no study has precisely identified the VPD breakpoints where genotypes restrict transpiration under natural conditions. Therefore, outdoors HTP data (15 min frequency) of a chickpea population were used to automate the generation of smooth transpiration profiles, extract informative features of the transpiration response to VPD for optimal genotypic discretization, identify VPD breakpoints, and compare genotypes. Results Fifteen biologically relevant features were extracted from the transpiration rate profiles derived from load cells data. Genotypes were clustered (C1, C2, C3) and 6 most important features (with heritability > 0.5) were selected using unsupervised Random Forest. All the wild relatives were found in C1, while C2 and C3 mostly comprised high TE and low TE lines, respectively. Assessment of the distinct p-value groups within each selected feature revealed highest genotypic variation for the feature representing transpiration response to high VPD condition. Sensitivity analysis on a multi-output neural network model (with R of 0.931, 0.944, 0.953 for C1, C2, C3, respectively) found C1 with the highest water saving ability, that restricted transpiration at relatively low VPD levels, 56% (i.e. 3.52 kPa) or 62% (i.e. 3.90 kPa), depending whether the influence of other environmental variables was minimum or maximum. Also, VPD appeared to have the most striking influence on the transpiration response independently of other environment variable, whereas light, temperature, and relative humidity alone had little/no effect. Conclusion Through this study, we present a novel approach to identifying genotypes with drought-tolerance potential, which overcomes the challenges in HTP of the water-saving trait. The six selected features served as proxy phenotypes for reliable genotypic discretization. The wild chickpeas were found to limit water-loss faster than the water-profligate cultivated ones. Such an analytic approach can be directly used for prescriptive breeding applications, applied to other traits, and help expedite maximized information extraction from HTP data.

LiDAR point clouds are characterized by high geometric and radiometric resolution and are therefore of great use for large-scale forest analysis. Although the analysis of 3D geometries and shapes has improved at different resolutions, processing large-scale 3D LiDAR point clouds is difficult due to their enormous volume. From the perspective of using LiDAR point clouds for forests, the challenge lies in learning local and global features, as the number of points in a typical 3D LiDAR point cloud is in the range of millions. In this research, we present a novel end-to-end deep learning framework called ADCoSNet, capable of adaptively reconstructing 3D LiDAR point clouds from a few sparse measurements. ADCoSNet uses empirical mode decomposition (EMD), a data-driven signal processing approach with Deep Learning, to decompose input signals into intrinsic mode functions (IMFs). These IMFs capture hierarchical implicit features in the form of decreasing spatial frequency. This research proposes using the last IMF (least varying component), also known as the Residual function, as a statistical prior for capturing local features, followed by fusing with the hierarchical convolutional features from the deep compressive sensing (CS) network. The central idea is that the Residue approximately represents the overall forest structure considering it is relatively homogenous due to the presence of vegetation. ADCoSNet utilizes this last IMF for generating sparse representation based on a set of CS measurement ratios. The research presents extensive experiments for reconstructing 3D LiDAR point clouds with high fidelity for various CS measurement ratios. Our approach achieves a maximum peak signal-to-noise ratio (PSNR) of 48.96 dB (approx. 8 dB better than reconstruction without data-dependent transforms) with reconstruction root mean square error (RMSE) of 7.21. It is envisaged that the proposed framework finds high potential as an end-to-end learning framework for generating adaptive and sparse representations to capture geometrical features for the 3D reconstruction of forests.

The rapid development of phenotyping technologies over the last years gave the opportunity to study plant development over time. The treatment of the massive amount of data collected by high-throughput phenotyping (HTP) platforms is however an important challenge for the plant science community. An important issue is to accurately estimate, over time, the genotypic component of plant phenotype. In outdoor and field-based HTP platforms, phenotype measurements can be substantially affected by data-generation inaccuracies or failures, leading to erroneous or missing data. To solve that problem, we developed an analytical pipeline composed of three modules: detection of outliers, imputation of missing values, and mixed-model genotype adjusted means computation with spatial adjustment. The pipeline was tested on three different traits (3D leaf area, projected leaf area, and plant height), in two crops (chickpea, sorghum), measured during two seasons. Using real-data analyses and simulations, we showed that the sequential application of the three pipeline steps was particularly useful to estimate smooth genotype growth curves from raw data containing a large amount of noise, a situation that is potentially frequent in data generated on outdoor HTP platforms. The procedure we propose can handle up to 50% of missing values. It is also robust to data contamination rates between 20 and 30% of the data. The pipeline was further extended to model the genotype time series data. A change-point analysis allowed the determination of growth phases and the optimal timing where genotypic differences were the largest. The estimated genotypic values were used to cluster the genotypes during the optimal growth phase. Through a two-way analysis of variance (ANOVA), clusters were found to be consistently defined throughout the growth duration. Therefore, we could show, on a wide range of scenarios, that the pipeline facilitated efficient extraction of useful information from outdoor HTP platform data. High-quality plant growth time series data is also provided to support breeding decisions. The R code of the pipeline is available at https://github.com/ICRISAT-GEMS/SpaTemHTP.

High-frequency monitoring of agrometeorological parameters is quintessential in the domain of Precision Agriculture (PA), where timeliness of collected observations and the ability to generate ahead-of-time predictions can substantially impact the crop yield. In this context, state-of-the-art internet-of-things (IoT)-based sensing platforms are often employed to generate, pre-process and assimilate real-time data from heterogeneous sensors and streaming data sources. Simultaneously, Time-Series Forecasting Algorithms (TSFAs) are responsible for generating reliable forecasts with a pre-defined forecast horizon and confidence. These TSFAs often rely on modelling the correlation between endogenous variables, the impact of exogenous variables on latent form and structural properties of data such as autocorrelation, periodicity, trend, pattern, and causality to approximate the model parameters. Traditionally, TSFAs such as the Holt–Winters (HW) and Autoregressive family of models (ARIMA) apply a linear and parametric approach towards model approximation, whilst models like Support Vector Regression (SVRs) and Neural Networks (NNs) adhere to a non-linear, non-parametric approach for modelling the historical data. Recently, Deep-Learning-based TSFAs such as Recurrent Neural Networks (RNNs), and Long-Short-Term-Memory (LSTMS) have gained popularity due to their capability to model long sequences of highly non-linear and stochastic data effectively. However, the evolution of TSFAs for predicting agrometeorological parameters pivots around one-step-ahead forecasting, which often overestimates the performance metrics defined for validating forecast capabilities of potential TSFAs. Hence, this paper attempts to evaluate and compare the performance of different machine learning (ML) and deep learning (DL) based TSFAs under one-step and multi-step-ahead forecast scenarios, thereby estimating the generalization capabilities of TSFA models over unseen data. The data used in this study are collected from an Automatic Weather Station (AWS), sampled at an interval of 15 min, and range over one month. Temperature (T) and Humidity (H) observations from the AWS are further converted into univariate, supervised time-series diurnal data profiles. Finally, walk-forward validation is used to evaluate recursive one-step-ahead forecasts until the desired prediction horizon is achieved. The results show that the Seasonal Auto-Regressive Integrated Moving Average (SARIMA) and SVR models outperform their DL-based counterparts in one-step and multi-step ahead settings with a fixed forecast horizon. This work aims to present a baseline comparison between different TSFAs to assist the process of model selection and facilitate rapid ahead-of-time forecasting for end-user applications.

Earth Observation data possess tremendous potential in understanding the dynamics of our planet. We propose the Semantics-driven Remote Sensing Scene Understanding (Sem-RSSU) framework for rendering comprehensive grounded spatio-contextual scene descriptions for enhanced situational awareness. To minimize the semantic gap for remote-sensing-scene understanding, the framework puts forward the transformation of scenes by using semantic-web technologies to Remote Sensing Scene Knowledge Graphs (RSS-KGs). The knowledge-graph representation of scenes has been formalized through the development of a Remote Sensing Scene Ontology (RSSO)—a core ontology for an inclusive remote-sensing-scene data product. The RSS-KGs are enriched both spatially and contextually, using a deductive reasoner, by mining for implicit spatio-contextual relationships between land-cover classes in the scenes. The Sem-RSSU, at its core, constitutes novel Ontology-driven Spatio-Contextual Triple Aggregation and realization algorithms to transform KGs to render grounded natural language scene descriptions. Considering the significance of scene understanding for informed decision-making from remote sensing scenes during a flood, we selected it as a test scenario, to demonstrate the utility of this framework. In that regard, a contextual domain knowledge encompassing Flood Scene Ontology (FSO) has been developed. Extensive experimental evaluations show promising results, further validating the efficacy of this framework.