Fusion neural networks for plant classification: learning to combine RGB, hyperspectral, and lidar data

Data science competition for cross-site individual tree species identification from airborne remote sensing data

Data on individual tree crowns from remote sensing have the potential to advance forest ecology by providing information about forest composition and structure with a continuous spatial coverage over large spatial extents. Classifying individual trees to their taxonomic species over large regions from remote sensing data is challenging. Methods to classify individual species are often accurate for common species, but perform poorly for less common species and when applied to new sites. We ran a data science competition to help identify effective methods for the task of classification of individual crowns to species identity. The competition included data from three sites to assess each methods' ability to generalize patterns across two sites simultaneously and apply methods to an untrained site. Three different metrics were used to assess and compare model performance. Six teams participated, representing four countries and nine individuals. The highest performing method from a previous competition in 2017 was applied and used as a baseline to understand advancements and changes in successful methods. The best species classification method was based on a two-stage fully connected neural network that significantly outperformed the baseline random forest and gradient boosting ensemble methods. All methods generalized well by showing relatively strong performance on the trained sites (accuracy = 0.46-0.55, macro F1 = 0.09-0.32, cross entropy loss = 2.4-9.2), but generally failed to transfer effectively to the untrained site (accuracy = 0.07-0.32, macro F1 = 0.02-0.18, cross entropy loss = 2.8-16.3). Classification performance was influenced by the number of samples with species labels available for training, with most methods predicting common species at the training sites well (maximum F1 score of 0.86) relative to the uncommon species where none were predicted. Classification errors were most common between species in the same genus and different species that occur in the same habitat. Most methods performed better than the baseline in detecting if a species was not in the training data by predicting an untrained mixed-species class, especially in the untrained site. This work has highlighted that data science competitions can encourage advancement of methods, particularly by bringing in new people from outside the focal discipline, and by providing an open dataset and evaluation criteria from which participants can learn.

Towards the fully automated monitoring of ecological communities

High-resolution monitoring is fundamental to understand ecosystems dynamics in an era of global change and biodiversity declines. While real-time and automated monitoring of abiotic components has been possible for some time, monitoring biotic components-for example, individual behaviours and traits, and species abundance and distribution-is far more challenging. Recent technological advancements offer potential solutions to achieve this through: (i) increasingly affordable high-throughput recording hardware, which can collect rich multidimensional data, and (ii) increasingly accessible artificial intelligence approaches, which can extract ecological knowledge from large datasets. However, automating the monitoring of facets of ecological communities via such technologies has primarily been achieved at low spatiotemporal resolutions within limited steps of the monitoring workflow. Here, we review existing technologies for data recording and processing that enable automated monitoring of ecological communities. We then present novel frameworks that combine such technologies, forming fully automated pipelines to detect, track, classify and count multiple species, and record behavioural and morphological traits, at resolutions which have previously been impossible to achieve. Based on these rapidly developing technologies, we illustrate a solution to one of the greatest challenges in ecology: the ability to rapidly generate high-resolution, multidimensional and standardised data across complex ecologies.

End-to-End Fusion of Hyperspectral and Chlorophyll Fluorescence Imaging to Identify Rice Stresses

Herbicides and heavy metals are hazardous substances of environmental pollution, resulting in plant stress and harming humans and animals. Identification of stress types can help trace stress sources, manage plant growth, and improve stress-resistant breeding. In this research, hyperspectral imaging (HSI) and chlorophyll fluorescence imaging (Chl-FI) were adopted to identify the rice plants under two types of herbicide stresses (butachlor (DCA) and quinclorac (ELK)) and two types of heavy metal stresses (cadmium (Cd) and copper (Cu)). Visible/near-infrared spectra of leaves (L-VIS/NIR) and stems (S-VIS/NIR) extracted from HSI and chlorophyll fluorescence kinetic curves of leaves (L-Chl-FKC) and stems (S-Chl-FKC) extracted from Chl-FI were fused to establish the models to detect the stress of the hazardous substances. Novel end-to-end deep fusion models were proposed for low-level, middle-level, and high-level information fusion to improve identification accuracy. Results showed that the high-level fusion-based convolutional neural network (CNN) models reached the highest detection accuracy (97.7%), outperforming the models using a single data source (<94.7%). Furthermore, the proposed end-to-end deep fusion models required a much simpler training procedure than the conventional two-stage deep learning fusion. This research provided an efficient alternative for plant stress phenotyping, including identifying plant stresses caused by hazardous substances of environmental pollution.