Using Unmanned Aerial Systems (UAS) and Object-Based Image Analysis (OBIA) for Measuring Plant-Soil Feedback Effects on Crop Productivity

SCAG: A Stratified, Clustered, and Growing-Based Algorithm for Soybean Branch Angle Extraction and Ideal Plant Architecture Evaluation

Three-dimensional (3D) phenotyping is important for studying plant structure and function. Light detection and ranging (LiDAR) has gained prominence in 3D plant phenotyping due to its ability to collect 3D point clouds. However, organ-level branch detection remains challenging due to small targets, sparse points, and low signal-to-noise ratios. In addition, extracting biologically relevant angle traits is difficult. In this study, we developed a stratified, clustered, and growing-based algorithm (SCAG) for soybean branch detection and branch angle calculation from LiDAR data, which is heuristic, open-source, and expandable. SCAG achieved high branch detection accuracy (F-score = 0.77) and branch angle calculation accuracy (r = 0.84) when evaluated on 152 diverse soybean varieties. Meanwhile, the SCAG outperformed 2 other classic algorithms, the support vector machine (F-score = 0.53) and density-based methods (F-score = 0.55). Moreover, after applying the SCAG to 405 soybean varieties over 2 consecutive years, we quantified various 3D traits, including canopy width, height, stem length, and average angle. After data filtering, we identified novel heritable and repeatable traits for evaluating soybean density tolerance potential, such as the ratio of average angle to height and the ratio of average angle to stem length, which showed greater potential than the well-known ratio of canopy width to height trait. Our work demonstrates remarkable advances in 3D phenotyping and plant architecture screening. The algorithm can be applied to other crops, such as maize and tomato. Our dataset, scripts, and software are public, which can further benefit the plant science community by enhancing plant architecture characterization and ideal variety selection.

Extraction of Broad-Leaved Tree Crown Based on UAV Visible Images and OBIA-RF Model: A Case Study for Chinese Olive Trees

Chinese olive trees (Canarium album L.) are broad-leaved species that are widely planted in China. Accurately obtaining tree crown information provides important data for evaluating Chinese olive tree growth status, water and fertilizer management, and yield estimation. To this end, this study first used unmanned aerial vehicle (UAV) images in the visible band as the source of remote sensing (RS) data. Second, based on spectral features of the image object, the vegetation index, shape, texture, and terrain features were introduced. Finally, the extraction effect of different feature dimensions was analyzed based on the random forest (RF) algorithm, and the performance of different classifiers was compared based on the features after dimensionality reduction. The results showed that the difference in feature dimensionality and importance was the main factor that led to a change in extraction accuracy. RF has the best extraction effect among the current mainstream machine learning (ML) algorithms. In comparison with the pixel-based (PB) classification method, the object-based image analysis (OBIA) method can extract features of each element of RS images, which has certain advantages. Therefore, the combination of OBIA and RF algorithms is a good solution for Chinese olive tree crown (COTC) extraction based on UAV visible band images.

Monitoring post-fire neighborhood competition effects on pine saplings under different environmental conditions by means of UAV multispectral data and structure-from-motion photogrammetry

In burned landscapes, the recruitment success of the tree dominant species mainly depends on plant competition mechanisms operating at fine spatial scale, that may hinder resource availability during the former years after the disturbance. Data acquisition at very high spatial resolution from unmanned aerial vehicles (UAV) have promoted new opportunities for understanding context-dependent competition processes in post-fire environments. Here, we explored the potentiality of UAV-borne data for assessing inter-specific competition effects of understory woody vegetation on pine saplings, as well as intra-specific interactions of neighboring saplings, across three burned landscapes located along a climatic/productivity gradient in the Iberian Peninsula. Geographic object-based image analysis (GEOBIA), including multiresolution segmentation and support vector machine (SVM) classification, was used to map pine saplings and understory shrubs at species level. Input data were, on the one hand, multispectral (11.31 cm·pixel^-1) and Structure-from-Motion (SfM) canopy height model (CHM) data fusion, hereafter MS-CHM, and, on the other, RGB (3.29 cm·pixel^-1) and CHM data fusion, hereafter RGB-CHM. A Random Forest (RF) regression algorithm was used to evaluate the effects of neighborhood competition on the relative growth in height of 50 pine saplings randomly sampled across the MS-CHM classified map. Circular plots of 3 m radius were set from the centroid of each target pine sapling to measure percentage cover, mean height of all individuals in the plot and mean height of individuals contacting the target sapling. Competing shrub species were differentiated according to their fire-adaptive traits (i.e. seeders vs resprouters). Object-based image classification applied on MS-CHM yielded higher overall accuracy for the three sites (83.67% ± 3.06%) than RGB-CHM (74.33% ± 3.21%). Intra-specific competitive effects were not detected, whereas increasing cover and height of shrub neighbors had a significant non-linear impact on the growth on pine saplings across the study sites. The strongest competitive effects of seeder shrubs occurred in open areas with low vegetation cover and fuel continuity, following a gap-dependent model. The non-linear relationships evidenced in this study between the structure of neighboring shrubs and the growth of pine seedlings/saplings have profound implications for considering possible competing thresholds in post-fire decision-making processes. These results endorse the use of UAV multispectral and SfM photogrammetry as a valuable post-fire management tool for measuring accurately the effect of competition in heterogeneous burned landscapes.

The role of soils in habitat creation, maintenance and restoration

Soils are the fundament of terrestrial ecosystems. Across the globe we find different soil types with different properties resulting from the interacting soil forming factors: parent material, climate, topography, organisms and time. Here we present the role of soils in habitat formation and maintenance in natural systems, and reflect on how humans have modified soils from local to global scale. Soils host a tremendous diversity of life forms, most of them microscopic in size. We do not yet know all the functionalities of this diversity at the level of individual taxa or through their interactions. However, we do know that the interactions and feedbacks between soil life, plants and soil chemistry and physics are essential for soil and habitat formation, maintenance and restoration. Moreover, the couplings between soils and major cycles of carbon, nutrients and water are essential for supporting the production of food, feed and fibre, drinking water and greenhouse gas balances. Soils take thousands of years to form, yet are lost very quickly through a multitude of stressors. The current status of our soils globally is worrisome, yet with concerted action we can bend the curve and create win-wins of soil and habitat conservation, regeneration and sustainable development. This article is part of the theme issue 'The role of soils in delivering Nature's Contributions to People'.