Tracking canopy gaps in mangroves remotely using deep learning

Abstract

Mangroves are among the most ecologically valuable ecosystems of the globe. Reliable remote sensing solutions are required to assist their management and conservation at broad scale. Canopy gaps are part of forests' turnover and rejuvenation, but yet no method has been proposed to map their occurrence and recovery in mangroves. Here, were propose an approach based on a deep learning framework called Mask R-CNN to achieve automatic detection and delineation of gaps using very-high-resolution satellite imagery (<1 m). The Mask R-CNN combines a series of neural network architectures to identify and delineate gaps, determine their recovery stage, and estimate their morphological attributes. The approach was tested on four mangroves from different regions of the globe with high concentration of gaps of various origins (lightning strikes, oil spills, cutting, pests). The Mask R-CNN performed well to detect gaps, and accurately delineated gap contours (F1-score of segmentation ≥0.89). The model also succeeded in distinguishing among five recovery stages of gaps, from their onset to closure (Overall Accuracy = 91.4, Kappa = 0.89). Accurate retrieval of gap area, eccentricity, and compactnessthree relevant morphological attributeswere obtained (R 2 ≥ 0.83, NRMSE ≤10%). Several sources of confusion and misdelineation were identified. Our approach shows promising transferability to other mangrove sites and optical sensors and could help monitor canopy recovery in mangroves. It also opens promising perspectives for identifying the origin of gaps (natural or human-induced). It is intended to assist environmental managers and field experts in the management and conservation of these fragile ecosystems.

Leveraging spatial content of images to enhance hyperspectral-multispectral fusion performance

“…Originally, the NNDiffuse algorithm was designed to be a radiometrically accurate pansharpening algorithm and has been used in both commercial geospatial packages (e.g., ENVI) as well as in research applications. [10][11][12][13][14] In previous work, 5,6 we demonstrated that NNDiffuse can be extended to the problem of LRHSI+HRMSI fusion, that is, spatially enhancing a low-res HSI using a high-res MSI. In Ref., 6 we explained in detail how the LRHSI+HRMSI fusion is broken down into b separate pansharpening tasks, where b is the number of highresolution bands in the HRMSI.…”

Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence

“…The semantic segmentation prediction also enables us to study the gaps between trees or those separating forest stands. This helps to understand the growth patterns of the whole mangrove forest and the species distributions, depending on environmental variables, such as distance to shore, tidal locations, forest cover loss and water channel formation [29]. It can also aid in detecting deforestation incidents or other disturbances in the environment.…”

“…Paired with machine learning automation, studies of long time-series of images can be carried out. Recent improvements in satellite image resolutions (i.e., 0.031 m for the World-View 3 satellite) have allowed for more resolved classification of trees using semantic segmentation neural networks [23,24], detection of individual trees using instance segmentation networks [25][26][27][28] and detection of mangrove forest clearings [29] on highresolution RGB images. Nonetheless, the calculation of certain variables, such as the height of trees extracted from canopy height models (CHMs) is error-prone at the current resolution of satellite imagery and should be paired with low-flying platforms, such as planes or UASs [28] for better validation and performance.…”

Image fusion of hyperspectral and multispectral imagery using nearest-neighbor diffusion

“…In Ref. 26, NNDiffuse was used to spatially enhance WV-3 and WorldView-4 images for tracking canopy gaps in mangroves using a Mask R-CNN algorithm. In Ref.…”