Skip to content

Earth observation analytics

A large and rapidly growing number of satellite instruments are providing ever more detailed observations of our planet. These can be used to understand and monitor critical environmental indicators, to better manage the environment, and to inform disaster preparedness and response.

The Monash Earth Observation Analytics Group is developing advanced technologies to extract more accurate information from satellite observations.

Our high resolution land use map of the State of Victoria can be found here.

Publications

A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping.
Lucas, B., Pelletier, C., Schmidt, D., Webb, G. I., & Petitjean, F.
Machine Learning, 112, 1941-1973, 2023.
[Bibtex] [Abstract]  → Access on publisher site

@Article{lucas2021bayesian,
author = {Lucas, Benjamin and Pelletier, Charlotte and Schmidt, Daniel and Webb, Geoffrey I and Petitjean, Fran{\c{c}}ois},
journal = {Machine Learning},
title = {A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping},
year = {2023},
pages = {1941-1973},
volume = {112},
abstract = {Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA) - where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known as semi-supervised DA, where some labelled samples are available in the target domain. In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from satellite image time series (SITS) data. The technique takes a convolutional neural network trained on a source domain and then trains further on the available target domain with a novel regularizer applied to the model weights. The regularizer adjusts the degree to which the model is modified to fit the target data, limiting the degree of change when the target data are few in number and increasing it as target data quantity increases. Our experiments on Sentinel-2 time series images compare Sourcerer with two state-of-the-art semi-supervised domain adaptation techniques and four baseline models. We show that on two different source-target domain pairings Sourcerer outperforms all other methods for any quantity of labelled target data available. In fact, the results on the more difficult target domain show that the starting accuracy of Sourcerer (when no labelled target data are available), 74.2%, is greater than the next-best state-of-the-art method trained on 20,000 labelled target instances.},
doi = {10.1007/s10994-020-05942-z},
keywords = {time series, earth observation analytics},
publisher = {Springer US},
related = {earth-observation-analytics},
}
ABSTRACT Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA) - where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known as semi-supervised DA, where some labelled samples are available in the target domain. In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from satellite image time series (SITS) data. The technique takes a convolutional neural network trained on a source domain and then trains further on the available target domain with a novel regularizer applied to the model weights. The regularizer adjusts the degree to which the model is modified to fit the target data, limiting the degree of change when the target data are few in number and increasing it as target data quantity increases. Our experiments on Sentinel-2 time series images compare Sourcerer with two state-of-the-art semi-supervised domain adaptation techniques and four baseline models. We show that on two different source-target domain pairings Sourcerer outperforms all other methods for any quantity of labelled target data available. In fact, the results on the more difficult target domain show that the starting accuracy of Sourcerer (when no labelled target data are available), 74.2%, is greater than the next-best state-of-the-art method trained on 20,000 labelled target instances.

Live fuel moisture content estimation from MODIS: A deep learning approach.
Zhu, L., Webb, G. I., Yebra, M., Scortechini, G., Miller, L., & Petitjean, F.
ISPRS Journal of Photogrammetry and Remote Sensing, 179, 81-91, 2021.
[Bibtex] [Abstract]  → Access on publisher site

@Article{ZHU202181,
author = {Liujun Zhu and Geoffrey I. Webb and Marta Yebra and Gianluca Scortechini and Lynn Miller and Francois Petitjean},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
title = {Live fuel moisture content estimation from MODIS: A deep learning approach},
year = {2021},
issn = {0924-2716},
pages = {81-91},
volume = {179},
abstract = {Live fuel moisture content (LFMC) is an essential variable to model fire danger and behaviour. This paper presents the first application of deep learning to LFMC estimation based on the historical LFMC ground samples of the Globe-LFMC database, as a step towards operational daily LFMC mapping in the Contiguous United States (CONUS). One-year MODerate resolution Imaging Spectroradiometer (MODIS) time series preceding each LFMC sample were extracted as the primary data source for training. The proposed temporal convolutional neural network for LFMC (TempCNN-LFMC) comprises three 1-D convolutional layers that learn the multi-scale temporal dynamics (features) of one-year MODIS time series specific to LFMC estimation. The learned features, together with a few auxiliary variables (e.g., digital elevation model), are then passed to three fully connected layers to extract the non-linear relationships with LFMC. In the primary training and validation scenario, the neural network was trained using samples from 2002 to 2013 and then adopted to estimating the LFMC from 2014 to 2018, achieving an overall root mean square error (RMSE) of 25.57% and a correlation coefficient (R) of 0.74. Good consistency on spatial patterns and temporal trends of accuracy was observed. The trained model achieved a similar RMSE of 25.98%, 25.20% and 25.93% for forest, shrubland, and grassland, respectively, without requiring prior information on the vegetation type.},
doi = {10.1016/j.isprsjprs.2021.07.010},
keywords = {time series, Live fuel moisture content, earth observation analytics, MODIS, Convolutional neural network, Time series analysis, Fire risk, Fire danger},
related = {earth-observation-analytics},
}
ABSTRACT Live fuel moisture content (LFMC) is an essential variable to model fire danger and behaviour. This paper presents the first application of deep learning to LFMC estimation based on the historical LFMC ground samples of the Globe-LFMC database, as a step towards operational daily LFMC mapping in the Contiguous United States (CONUS). One-year MODerate resolution Imaging Spectroradiometer (MODIS) time series preceding each LFMC sample were extracted as the primary data source for training. The proposed temporal convolutional neural network for LFMC (TempCNN-LFMC) comprises three 1-D convolutional layers that learn the multi-scale temporal dynamics (features) of one-year MODIS time series specific to LFMC estimation. The learned features, together with a few auxiliary variables (e.g., digital elevation model), are then passed to three fully connected layers to extract the non-linear relationships with LFMC. In the primary training and validation scenario, the neural network was trained using samples from 2002 to 2013 and then adopted to estimating the LFMC from 2014 to 2018, achieving an overall root mean square error (RMSE) of 25.57% and a correlation coefficient (R) of 0.74. Good consistency on spatial patterns and temporal trends of accuracy was observed. The trained model achieved a similar RMSE of 25.98%, 25.20% and 25.93% for forest, shrubland, and grassland, respectively, without requiring prior information on the vegetation type.

No Cloud on the Horizon: Probabilistic Gap Filling in Satellite Image Series.
Fischer, R., Piatkowski, N., Pelletier, C., Webb, G. I., Petitjean, F., & Morik, K.
IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), pp. 546-555, 2020.
[Bibtex] [Abstract]  → Access on publisher site

@InProceedings{Fischer2020,
author = {Raphael Fischer and Nico Piatkowski and Charlotte Pelletier and Geoffrey I. Webb and Francois Petitjean and Katharina Morik},
booktitle = {{IEEE} 7th International Conference on Data Science and Advanced Analytics ({DSAA})},
title = {No Cloud on the Horizon: Probabilistic Gap Filling in Satellite Image Series},
year = {2020},
pages = {546-555},
publisher = {{IEEE}},
abstract = {Spatio-temporal data sets such as satellite image series are of utmost importance for understanding global developments like climate change or urbanization. However, incompleteness of data can greatly impact usability and knowledge discovery. In fact, there are many cases where not a single data point in the set is fully observed. For filling gaps, we introduce a novel approach that utilizes Markov random fields (MRFs). We extend the probabilistic framework to also consider empirical prior information, which allows to train even on highly incomplete data. Moreover, we devise a way to make discrete MRFs predict continuous values via state superposition. Experiments on real-world remote sensing imagery suffering from cloud cover show that the proposed approach outperforms state-of-the-art gap filling techniques.},
doi = {10.1109/dsaa49011.2020.00069},
keywords = {earth observation analytics},
related = {earth-observation},
}
ABSTRACT Spatio-temporal data sets such as satellite image series are of utmost importance for understanding global developments like climate change or urbanization. However, incompleteness of data can greatly impact usability and knowledge discovery. In fact, there are many cases where not a single data point in the set is fully observed. For filling gaps, we introduce a novel approach that utilizes Markov random fields (MRFs). We extend the probabilistic framework to also consider empirical prior information, which allows to train even on highly incomplete data. Moreover, we devise a way to make discrete MRFs predict continuous values via state superposition. Experiments on real-world remote sensing imagery suffering from cloud cover show that the proposed approach outperforms state-of-the-art gap filling techniques.

Unsupervised Domain Adaptation Techniques for Classification of Satellite Image Time Series.
Lucas, B., Pelletier, C., Schmidt, D., Webb, G. I., & Petitjean, F.
IEEE International Geoscience and Remote Sensing Symposium, pp. 1074–1077, 2020.
[Bibtex] [Abstract]  → Access on publisher site

@InProceedings{lucas2020unsupervised,
author = {Lucas, Benjamin and Pelletier, Charlotte and Schmidt, Daniel and Webb, Geoffrey I and Petitjean, Fran{\c{c}}ois},
booktitle = {IEEE International Geoscience and Remote Sensing Symposium},
title = {Unsupervised Domain Adaptation Techniques for Classification of Satellite Image Time Series},
year = {2020},
organization = {IEEE},
pages = {1074--1077},
abstract = {Land cover maps are vitally important to many elements of environmental management. However the machine learning algorithms used to produce them require a substantive quantity of labelled training data to reach the best levels of accuracy. When researchers wish to map an area where no labelled training data are available, one potential solution is to use a classifier trained on another geographical area and adapting it to the target location-this is known as Unsupervised Domain Adaptation (DA). In this paper we undertake the first experiments using unsupervised DA methods for the classification of satellite image time series (SITS) data. Our experiments draw the interesting conclusion that existing methods provide no benefit when used on SITS data, and that this is likely due to the temporal nature of the data and the change in class distributions between the regions. This suggests that an unsupervised domain adaptation technique for SITS would be extremely beneficial for land cover mapping.},
doi = {10.1109/IGARSS39084.2020.9324339},
keywords = {time series, earth observation analytics},
related = {scalable-time-series-classifiers},
}
ABSTRACT Land cover maps are vitally important to many elements of environmental management. However the machine learning algorithms used to produce them require a substantive quantity of labelled training data to reach the best levels of accuracy. When researchers wish to map an area where no labelled training data are available, one potential solution is to use a classifier trained on another geographical area and adapting it to the target location-this is known as Unsupervised Domain Adaptation (DA). In this paper we undertake the first experiments using unsupervised DA methods for the classification of satellite image time series (SITS) data. Our experiments draw the interesting conclusion that existing methods provide no benefit when used on SITS data, and that this is likely due to the temporal nature of the data and the change in class distributions between the regions. This suggests that an unsupervised domain adaptation technique for SITS would be extremely beneficial for land cover mapping.

AI for monitoring the Sustainable Development Goals and supporting and promoting action and policy development.
Miller, L., Bolton, M., Boulton, J., Mintrom, M., Nicholson, A., Rüdiger, C., Skinner, R., Raven, R., & Webb, G. I.
IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G), pp. 180-185, 2020.
[Bibtex] [Abstract]  → Access on publisher site

@InProceedings{miller2020ai,
author = {Miller, Lynn and Bolton, Mitzi and Boulton, Julie and Mintrom, Michael and Nicholson, Ann and R{\"u}diger, Christoph and Skinner, Rob and Raven, Rob and Webb, Geoffrey I},
booktitle = {IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G)},
title = {AI for monitoring the Sustainable Development Goals and supporting and promoting action and policy development},
year = {2020},
organization = {IEEE},
pages = {180-185},
abstract = {The United Nations sustainable development goals (SDGs) were ratified with much enthusiasm by all UN member states in 2015. However, subsequent progress to meet these goals has been hampered by a lack of data available to measure the SDG indicators (SDIs), and a lack of evidence-based insights to inform effective policy responses. We outline an interdisciplinary program of research into the use of artificial intelligence techniques to support measurement of the SDIs, using both machine learning methods to model SDI measurements and explainable AI techniques to present the outputs in a human-friendly manner. As well as addressing the technical concerns, we will investigate the governance issues of what forms of evidence, methods of collecting that evidence and means of its communication will most usefully inform effective policy development. By addressing these fundamental challenges, we aim to provide policy makers with the evidence needed to take effective action towards realising the Sustainable Development Goals.},
doi = {10.1109/AI4G50087.2020.9311014},
keywords = {earth observation analytics},
related = {earth-observation-analytics},
}
ABSTRACT The United Nations sustainable development goals (SDGs) were ratified with much enthusiasm by all UN member states in 2015. However, subsequent progress to meet these goals has been hampered by a lack of data available to measure the SDG indicators (SDIs), and a lack of evidence-based insights to inform effective policy responses. We outline an interdisciplinary program of research into the use of artificial intelligence techniques to support measurement of the SDIs, using both machine learning methods to model SDI measurements and explainable AI techniques to present the outputs in a human-friendly manner. As well as addressing the technical concerns, we will investigate the governance issues of what forms of evidence, methods of collecting that evidence and means of its communication will most usefully inform effective policy development. By addressing these fundamental challenges, we aim to provide policy makers with the evidence needed to take effective action towards realising the Sustainable Development Goals.

Deep Learning for the Classification of Sentinel-2 Image Series.
Pelletier, C., Webb, G. I., & Petitjean, F.
IEEE International Geoscience And Remote Sensing Symposium, 2019.
[Bibtex] [Abstract]  → Access on publisher site

@InProceedings{PelletierEtAl19b,
author = {Pelletier, Charlotte and Webb, Geoffrey I. and Petitjean, Francois},
booktitle = {IEEE International Geoscience And Remote Sensing Symposium},
title = {Deep Learning for the Classification of Sentinel-2 Image Series},
year = {2019},
month = {Jul},
abstract = {Satellite image time series (SITS) have proven to be essential for accurate and up-to-date land cover mapping over large areas. Most works about SITS have focused on the use of traditional classification algorithms such as Random Forests (RFs). Deep learning algorithms have been very successful for supervised tasks, in particular for data that exhibit a structure between attributes, such as space or time. In this work, we compare for the first time RFs to the two leading deep learning algorithms for handling temporal data: Recurrent Neural Networks (RNNs) and temporal Convolutional Neural Networks (TempCNNs). We carry out a large experiment using Sentinel-2 time series. We compare both accuracy and computational times to classify 10,980 km 2 over Australia. The results highlights the good performance of TemCNNs that obtain the highest accuracy. They also show that RNNs might be less suited for large scale study as they have higher runtime complexity.},
doi = {10.1109/IGARSS.2019.8900123},
keywords = {time series, earth observation analytics},
related = {earth-observation-analytics},
}
ABSTRACT Satellite image time series (SITS) have proven to be essential for accurate and up-to-date land cover mapping over large areas. Most works about SITS have focused on the use of traditional classification algorithms such as Random Forests (RFs). Deep learning algorithms have been very successful for supervised tasks, in particular for data that exhibit a structure between attributes, such as space or time. In this work, we compare for the first time RFs to the two leading deep learning algorithms for handling temporal data: Recurrent Neural Networks (RNNs) and temporal Convolutional Neural Networks (TempCNNs). We carry out a large experiment using Sentinel-2 time series. We compare both accuracy and computational times to classify 10,980 km 2 over Australia. The results highlights the good performance of TemCNNs that obtain the highest accuracy. They also show that RNNs might be less suited for large scale study as they have higher runtime complexity.

Using Sentinel-2 Image Time Series to map the State of Victoria, Australia.
Pelletier, C., Ji, Z., Hagolle, O., Morse-McNabb, E., Sheffield, K., Webb, G. I., & Petitjean, F.
Proceedings 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images, MultiTemp 2019, 2019.
[Bibtex] [Abstract]  → Access on publisher site

@InProceedings{PelletierEtAl19c,
author = {Pelletier, C. and Ji, Z. and Hagolle, O. and Morse-McNabb, E. and Sheffield, K. and Webb, G. I. and Petitjean, F.},
booktitle = {Proceedings 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images, MultiTemp 2019},
title = {Using Sentinel-2 Image Time Series to map the State of Victoria, Australia},
year = {2019},
abstract = {Sentinel-2 satellites are now acquiring images of the entire Earth every five days from 10 to 60 m spatial resolution. The supervised classification of this new optical image time series allows the operational production of accurate land cover maps over large areas. In this paper, we investigate the use of one year of Sentinel-2 data to map the state of Victoria in Australia. In particular, we produce two land cover maps using the most established and advanced algorithms in time series classification: Random Forest (RF) and Temporal Convolutional Neural Network (TempCNN). To our knowledge, these are the first land cover maps at 10 m spatial resolution for an Australian state.},
doi = {10.1109/Multi-Temp.2019.8866921},
keywords = {cartography;convolutional neural nets;geophysical image processing;image classification;image resolution;land cover;optical images;optical information processing;remote sensing;terrain mapping;time series;TempCNN;temporal convolutional neural network;random forest;land cover maps;Victoria state;Australian state;spatial resolution;time series classification;Sentinel-2 data;accurate land cover maps;operational production;optical image time series;supervised classification;Sentinel-2 satellites;Australia;sentinel-2 image time series;Radio frequency;Australia;Spatial resolution;Time series analysis;Agriculture;Convolutional neural networks;Sentinel-2 images;land cover map;time series;Temporal Convolutional Neural Networks;Random Forests;earth observation analytics},
related = {earth-observation-analytics},
}
ABSTRACT Sentinel-2 satellites are now acquiring images of the entire Earth every five days from 10 to 60 m spatial resolution. The supervised classification of this new optical image time series allows the operational production of accurate land cover maps over large areas. In this paper, we investigate the use of one year of Sentinel-2 data to map the state of Victoria in Australia. In particular, we produce two land cover maps using the most established and advanced algorithms in time series classification: Random Forest (RF) and Temporal Convolutional Neural Network (TempCNN). To our knowledge, these are the first land cover maps at 10 m spatial resolution for an Australian state.

Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series.
Pelletier, C., Webb, G. I., & Petitjean, F.
Remote Sensing, 11(5), Art. no. 523, 2019.
exclamation Clarivate Web of Science Highly Cited Paper 2021 - 2023
[Bibtex] [Abstract]  → Access on publisher site

@Article{PelletierEtAl19,
author = {Pelletier, Charlotte and Webb, Geoffrey I. and Petitjean, Francois},
journal = {Remote Sensing},
title = {Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series},
year = {2019},
issn = {2072-4292},
number = {5},
volume = {11},
abstract = {Latest remote sensing sensors are capable of acquiring high spatial and spectral Satellite Image Time Series (SITS) of the world. These image series are a key component of classification systems that aim at obtaining up-to-date and accurate land cover maps of the Earth’s surfaces. More specifically, current SITS combine high temporal, spectral and spatial resolutions, which makes it possible to closely monitor vegetation dynamics. Although traditional classification algorithms, such as Random Forest (RF), have been successfully applied to create land cover maps from SITS, these algorithms do not make the most of the temporal domain. This paper proposes a comprehensive study of Temporal Convolutional Neural Networks (TempCNNs), a deep learning approach which applies convolutions in the temporal dimension in order to automatically learn temporal (and spectral) features. The goal of this paper is to quantitatively and qualitatively evaluate the contribution of TempCNNs for SITS classification, as compared to RF and Recurrent Neural Networks (RNNs) —a standard deep learning approach that is particularly suited to temporal data. We carry out experiments on Formosat-2 scene with 46 images and one million labelled time series. The experimental results show that TempCNNs are more accurate than the current state of the art for SITS classification. We provide some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size; we also draw out some differences with standard results in computer vision (e.g., about pooling layers). Finally, we assess the visual quality of the land cover maps produced by TempCNNs.},
articlenumber = {523},
comment = {Clarivate Web of Science Highly Cited Paper 2021 - 2023},
doi = {10.3390/rs11050523},
keywords = {time series, earth observation analytics},
related = {earth-observation-analytics},
}
ABSTRACT Latest remote sensing sensors are capable of acquiring high spatial and spectral Satellite Image Time Series (SITS) of the world. These image series are a key component of classification systems that aim at obtaining up-to-date and accurate land cover maps of the Earth’s surfaces. More specifically, current SITS combine high temporal, spectral and spatial resolutions, which makes it possible to closely monitor vegetation dynamics. Although traditional classification algorithms, such as Random Forest (RF), have been successfully applied to create land cover maps from SITS, these algorithms do not make the most of the temporal domain. This paper proposes a comprehensive study of Temporal Convolutional Neural Networks (TempCNNs), a deep learning approach which applies convolutions in the temporal dimension in order to automatically learn temporal (and spectral) features. The goal of this paper is to quantitatively and qualitatively evaluate the contribution of TempCNNs for SITS classification, as compared to RF and Recurrent Neural Networks (RNNs) —a standard deep learning approach that is particularly suited to temporal data. We carry out experiments on Formosat-2 scene with 46 images and one million labelled time series. The experimental results show that TempCNNs are more accurate than the current state of the art for SITS classification. We provide some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size; we also draw out some differences with standard results in computer vision (e.g., about pooling layers). Finally, we assess the visual quality of the land cover maps produced by TempCNNs.

Exploring Data Quantity Requirements for Domain Adaptation in the Classification of Satellite Image Time Series.
Lucas, B., Pelletier, C., Inglada, J., Schmidt, D., Webb, G. I., & Petitjean, F.
Proceedings 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images, MultiTemp 2019, 2019.
[Bibtex] [Abstract]  → Access on publisher site

@InProceedings{LucasEtAl2019b,
author = {Lucas, B. and Pelletier, C. and Inglada, J. and Schmidt, D. and Webb, G. I. and Petitjean, F},
booktitle = {Proceedings 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images, MultiTemp 2019},
title = {Exploring Data Quantity Requirements for Domain Adaptation in the Classification of Satellite Image Time Series},
year = {2019},
publisher = {IEEE, Institute of Electrical and Electronics Engineers},
abstract = {Land cover maps are a vital input variable in all types of environmental research and management. However the modern state-of-The-Art machine learning techniques used to create them require substantial training data to produce optimal accuracy. Domain Adaptation is one technique researchers might use when labelled training data are unavailable or scarce. This paper looks at the result of training a convolutional neural network model on a region where data are available (source domain), and then adapting this model to another region (target domain) by retraining it on the available labelled data, and in particular how these results change with increasing data availability. Our experiments performing domain adaptation on satellite image time series, draw three interesting conclusions: (1) a model trained only on data from the source domain delivers 73.0% test accuracy on the target domain; (2) when all of the weights are retrained on the target data, over 16,000 instances were required to improve upon the accuracy of the source-only model; and (3) even if sufficient data is available in the target domain, using a model pretrained on a source domain will result in better overall test accuracy compared to a model trained on target domain data only-88.9% versus 84.7%.},
doi = {10.1109/Multi-Temp.2019.8866898},
keywords = {time series, earth observation analytics},
related = {earth-observation-analytics},
}
ABSTRACT Land cover maps are a vital input variable in all types of environmental research and management. However the modern state-of-The-Art machine learning techniques used to create them require substantial training data to produce optimal accuracy. Domain Adaptation is one technique researchers might use when labelled training data are unavailable or scarce. This paper looks at the result of training a convolutional neural network model on a region where data are available (source domain), and then adapting this model to another region (target domain) by retraining it on the available labelled data, and in particular how these results change with increasing data availability. Our experiments performing domain adaptation on satellite image time series, draw three interesting conclusions: (1) a model trained only on data from the source domain delivers 73.0% test accuracy on the target domain; (2) when all of the weights are retrained on the target data, over 16,000 instances were required to improve upon the accuracy of the source-only model; and (3) even if sufficient data is available in the target domain, using a model pretrained on a source domain will result in better overall test accuracy compared to a model trained on target domain data only-88.9% versus 84.7%.