From Remote Sensing to Multiple Time-Horizons Forecasts: Transformers Model for CyanoHAB Intensity in Lake Champlain
Jan 1, 2026·
,,,,,,,,,,,·
1 min read
Muhammad Adil
Patrick J. Clemins
Andrew W. Schroth
Panagiotis D. Oikonomou
Donna M. Rizzo
Peter D. F. Isles
Xiaohan Zhang
Kareem I. Hannoun
Scott Turnbull
Noah B. Beckage
Asim Zia
Safwan Wshah
Abstract
This work presents a remote-sensing-only forecasting framework for cyanobacterial harmful algal bloom intensity in Lake Champlain. The model combines Transformers and BiLSTM to predict bloom intensity up to 14 days ahead from satellite-derived cyanobacterial index and temperature signals, using a preprocessing pipeline designed to handle severe temporal sparsity. Reported results show strong performance across short- and medium-range horizons, supporting early warning for bloom monitoring and management.
Type
Publication
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 19, 6728-6750
Published in IEEE JSTARS in 2026. The paper introduces a Transformer-BiLSTM forecasting pipeline for CyanoHAB intensity prediction in Lake Champlain using only satellite-derived observations.
