Journal
REMOTE SENSING
Volume 14, Issue 19, Pages -Publisher
MDPI
DOI: 10.3390/rs14194957
Keywords
temporal convolutional networks; convolutional neural networks; long short-term memory; temporal deep learning; spatiotemporal deep learning; CNN-TCN; CNN-LSTM; land cover change; neighborhood size effects
Categories
Funding
- Natural Sciences and Engineering Research Council (NSERC) of Canada Postgraduate Scholarship-Doctoral Grant (PGS-D) [RGPIN-2017-03939]
Ask authors/readers for more resources
This study evaluates the impact of neighborhood size on the capability of deep learning models to forecast land cover changes and examines the effect of auxiliary spatial variables on the model's capacity. The findings suggest that increasing the neighborhood size improves the model's ability to predict short-term land cover changes. CNN-TCN models perform the best in forecasting land cover changes for several regions when additional spatial variables are provided.
Land cover change (LCC) studies are increasingly using deep learning (DL) modeling techniques. Past studies have leveraged temporal or spatiotemporal sequences of historical LC data to forecast changes with DL models. However, these studies do not adequately assess the association between neighborhood size and DL model capability to forecast LCCs, where neighborhood size refers to the spatial extent captured by each data sample. The objectives of this research study were to: (1) evaluate the effect of neighborhood size on the capacity of DL models to forecast LCCs, specifically Temporal Convolutional Networks (TCN) and Convolutional Neural Networks (CNN-TCN), and (2) assess the effect of auxiliary spatial variables on model capacity to forecast LCCs. First, each model type and neighborhood setting configuration was assessed using data derived from multitemporal MODIS LC for the Regional District of Bulkley-Nechako, Canada, comparing subareas exhibiting different amounts of LCCs with trends obtained for the full region. Next, outcomes were compared with three other study regions. The modeling results were evaluated with three-map comparison measures, where the real-world LC for the next timestep, the real-world LC for the previous timestep, and the forecasted LC for the next year were used to calculate correctly transitioned areas. Across all regions explored, it was observed that increasing neighborhood sizes improved the DL model's capabilities to forecast short-term LCCs. CNN-TCN models forecasted the most correct LCCs for several regions while reducing error due to quantity when provided additional spatial variables. This study contributes to the systematic exploration of neighborhood sizes on selected spatiotemporal DL techniques for geographic applications.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available