Journal Article

Tracking canopy gaps in mangroves remotely using deep learning

Disney, Mat, Souza Filho, Carlos Roberto, Friess, Dan, Lassalle, Guillaume

2022

Overview

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 compactness – three relevant morphological attributes – were obtained (R2 ≥ 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. Canopy gaps greatly contribute to mangrove forest turnover and rejuvenation. While gap monitoring is usually performed by field and aerial surveys, we propose a novel method based on deep learning to achieve this automatically from very‐high‐resolution satellite imagery. A multi‐task neural network is applied to the images to accurately detect and delineate gaps, and to determine their recovery stage. Our method proved reliable in various forests of the globe with contrasting characteristics and could therefore improve mangrove conservation and monitoring. Our study also opens perspectives to identify the origin of gaps, including those caused by human activities.

• Publisher: John Wiley & Sons, Inc,Wiley
• Subject: Artificial neural networks / Canopies / Canopy gap / Canopy gaps / Classification / Computer architecture / Conservation / Deep learning / Environmental management / forest conservation / Image segmentation / Lightning / Lightning strikes / mangrove / Mangroves / Morphology / National parks / Neural networks / Oil spills / Optical measuring instruments / Pests / Recovery / Remote sensing / Satellite imagery / Sediments / Strategic management / Trees / Vegetation