Plant phenomics (PP) has been recognized as a bottleneck in studying the interactions of genomics and environment on plants, limiting the progress of smart breeding and precise cultivation. High-throughput plant phenotyping is challenging owing to the spatio-temporal dynamics of traits. Proximal and remote sensing (PRS) techniques are increasingly used for plant phenotyping because of their advantages in multi-dimensional data acquisition and analysis. Substantial progress of PRS applications in PP has been observed over the last two decades and is analyzed here from an interdisciplinary perspective based on 2972 publications. This progress covers most aspects of PRS application in PP, including patterns of global spatial distribution and temporal dynamics, specific PRS technologies, phenotypic research fields, working environments, species, and traits. Subsequently, we demonstrate how to link PRS to multi-omics studies, including how to achieve multi-dimensional PRS data acquisition and processing, how to systematically integrate all kinds of phenotypic information and derive phenotypic knowledge with biological significance, and how to link PP to multi-omics association analysis. Finally, we identify three future perspectives for PRS-based PP: (1) strengthening the spatial and temporal consistency of PRS data, (2) exploring novel phenotypic traits, and (3) facilitating multi-omics communication.

Regional landslide identification is important for the risk management of landslide hazards. The traditional methods of regional landslide identification were mainly conducted by a human being. In previous studies, automatic landslide recognition mainly focused on new landslides distinct from the environment induced by rainfall or earthquake, using the image classification method and semantic segmentation method of deep learning. However, there is a lack of research on the automatic recognition of old loess landslides, which are difficult to distinguish from the environment. Therefore, this study uses the object detection method of deep learning to identify old loess landslides with Google Earth images. At first, a database of loess historical landslide samples was established for deep learning based on Google Earth images. A total of 6111 landslides were interpreted in three landslide areas in Gansu Province, China. Second, three object detection algorithms including the one-stage algorithm RetinaNet and YOLO v3 and the two-stage algorithm Mask R-CNN, were chosen for automatic landslide identification. Mask R-CNN achieved the greatest accuracy, with an AP of 18.9% and F1-score of 55.31%. Among the three landslide areas, the order of identification accuracy from high to low was Site 1, Site 2, and Site 3, with the F1-scores of 62.05%, 61.04% and 50.88%, respectively, which were positively related to their recognition difficulty. The research results proved that the object detection method can be employed for the automatic identification of loess landslides based on Google Earth images.

Wheat yield and grain protein content (GPC) are two main optimization targets for breeding and cultivation. Remote sensing provides nondestructive and early predictions of yield and GPC, respectively. However, whether it is possible to simultaneously predict yield and GPC in one model and the accuracy and influencing factors are still unclear. In this study, we made a systematic comparison of different deep learning models in terms of data fusion, time-series feature extraction, and multitask learning. The results showed that time-series data fusion significantly improved yield and GPC prediction accuracy with values of 0.817 and 0.809. Multitask learning achieved simultaneous prediction of yield and GPC with comparable accuracy to the single-task model. We further proposed a two-to-two model that combines data fusion (two kinds of data sources for input) and multitask learning (two outputs) and compared different feature extraction layers, including RNN (recurrent neural network), LSTM (long short-term memory), CNN (convolutional neural network), and attention module. The two-to-two model with the attention module achieved the best prediction accuracy for yield () and GPC (). The temporal distribution of feature importance was visualized based on the attention feature values. Although the temporal patterns of structural traits and spectral traits were inconsistent, the overall importance of both structural traits and spectral traits at the postanthesis stage was more important than that at the preanthesis stage. This study provides new insights into the simultaneous prediction of yield and GPC using deep learning from time-series proximal sensing, which may contribute to the accurate and efficient predictions of agricultural production.

Forest inventory holds an essential role in forest management and research, but the existing field inventory methods are highly time-consuming and labor-intensive. Here, we developed a simultaneous localization and mapping-based backpack light detection and ranging (LiDAR) system with dual orthogonal laser scanners and an open-source Python package called Forest3D for efficient and accurate forest inventory applications. Two key forest inventory variables, tree height and diameter at breast height (DBH), were extracted at six study sites with different tree species compositions. In addition, the vertical point density distribution and leaf area density (LAD) were calculated for two complex natural forest sites. The results showed that the backpack LiDAR system together with the Forest3D package accurately estimated the tree height (R² = 0.65, RMSE = 1.90 m) and DBH (R² = 0.95, RMSE = 0.02 m), which were equivalent to those derived from terrestrial laser scanning (TLS), but with much higher efficiency. The point density of the backpack LiDAR data was higher than or the same as that of the TLS data across all height strata, and the estimated LAD fit well with the TLS estimates (R² > 0.92, RMSE = 0.01 m²/m³). The backpack LiDAR system, along with the Forest3D package, provides an efficient and accurate solution for extracting forest inventory variables, which should be of great interests to forest managers and researchers.

Airborne laser scanning (ALS) data is one of the most commonly used data for terrain products generation. Filtering ground points is a prerequisite step for ALS data processing. Traditional filtering methods mainly use handcrafted features or predefined classification rules with pre-processing/post-processing operations to filter ground points iteratively, which is empirical and cumbersome. Deep learning provides a new approach to solve classification and segmentation problems because of its ability to self-learn features, which has been favored in many fields, particularly remote sensing. In this study, we proposed a point-based fully convolutional neural network (PFCN) which directly consumed points with only geometric information and extracted both point-wise and tile-wise features to classify each point. The network was trained with 37449157 points from 14 sites and evaluated on 6 sites in various forested environments. Additionally, the method was compared with five widely used filtering methods and one of the best point-based deep learning methods (PointNet++). Results showed that the PFCN achieved the best results in terms of mean omission error (T1 = 1.10%), total error (Te = 1.73%), and kappa coefficient (93.88%), but ranked second for the root mean square error of the digital terrain model caused by the worst commission error. Additionally, our method was on par with or even better than PointNet++ in accuracy. Moreover, our method consumes one-third of the computational resource and one-seventh of the training time. We believe that PFCN is a simple and flexible method that can be widely applied for ground point filtering.