# Attention-augmented Spatio-Temporal Segmentation for Land Cover Mapping

arXiv: https://arxiv.org/abs/2105.02963 · HTML: https://mlsanity.com/paper/2105.02963/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 2 May 2021.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping](https://mlsanity.com/paper/1510.00098/) (2015)
- [Time-Space tradeoff in deep learning models for crop classification on satellite multi-spectral image time series](https://mlsanity.com/paper/1901.10503/) (2019)
- [Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery](https://mlsanity.com/paper/1811.02471/) (2018)
- [Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN)](https://mlsanity.com/paper/2004.12880/) (2020)
- [Segmentation of Satellite Imagery using U-Net Models for Land Cover Classification](https://mlsanity.com/paper/2003.02899/) (2020)
- [Semi-supervised Classification using Attention-based Regularization on Coarse-resolution Data](https://mlsanity.com/paper/2001.00994/) (2020)
- [Land Cover Change Detection via Semantic Segmentation](https://mlsanity.com/paper/1911.12903/) (2019)

## Built on by (most cited first, 7 of 7)

- [Mapping smallholder cashew plantations to inform sustainable tree crop expansion in Benin](https://mlsanity.com/paper/2301.00363/) (2023)
- [CalCROP21: A Georeferenced multi-spectral dataset of Satellite Imagery and Crop Labels](https://mlsanity.com/paper/2107.12499/) (2021)
- [Clustering augmented Self-Supervised Learning: Anapplication to Land Cover Mapping](https://mlsanity.com/paper/2108.07323/) (2021)
- [Combining Satellite and Weather Data for Crop Type Mapping: An Inverse Modelling Approach](https://mlsanity.com/paper/2401.15875/) (2024)
- [Can SAM recognize crops? Quantifying the zero-shot performance of a semantic segmentation foundation model on generating crop-type maps using satellite imagery for precision agriculture](https://mlsanity.com/paper/2311.15138/) (2023)
- [Towards Knowledge Guided Pretraining Approaches for Multimodal Foundation Models: Applications in Remote Sensing](https://mlsanity.com/paper/2407.19660/) (2024)
- [Tools for Extracting Spatio-Temporal Patterns in Meteorological Image Sequences: From Feature Engineering to Attention-Based Neural Networks](https://mlsanity.com/paper/2210.12310/) (2022)

## Abstract (arXiv)

The availability of massive earth observing satellite data provide huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the existence of various land cover classes, noisy data, and the lack of proper labels. Also, each land cover class typically has its own unique temporal pattern and can be identified only during certain periods. In this article, we introduce a novel architecture that incorporates the UNet structure with Bidirectional LSTM and Attention mechanism to jointly exploit the spatial and temporal nature of satellite data and to better identify the unique temporal patterns of each land cover. We evaluate this method for mapping crops in multiple regions over the world. We compare our method with other state-of-the-art methods both quantitatively and qualitatively on two real-world datasets which involve multiple land cover classes. We also visualise the attention weights to study its effectiveness in mitigating noise and identifying discriminative time period.