Search

Satellite image time series (SITS) is a sequence of satellite images that record a given area at several consecutive times. The aim of such sequences is to use not only spatial information but also the temporal dimension of the data, which is used for multiple real-world applications, such as classification, segmentation, anomaly detection, and prediction. Several traditional machine learning algorithms have been developed and successfully applied to time series for predictions. However, these methods have limitations in some situations, thus deep learning (DL) techniques have been introduced to achieve the best performance. Reviews of machine learning and DL methods for time series prediction problems have been conducted in previous studies. However, to the best of our knowledge, none of these surveys have addressed the specific case of works using DL techniques and satellite images as datasets for predictions. Therefore, this paper concentrates on the DL applications for SITS prediction, giving an overview of the main elements used to design and evaluate the predictive models, namely the architectures, data, optimization functions, and evaluation metrics. The reviewed DL-based models are divided into three categories, namely recurrent neural network-based models, hybrid models, and feed-forward-based models (convolutional neural networks and multi-layer perceptron). The main characteristics of satellite images and the major existing applications in the field of SITS prediction are also presented in this article. These applications include weather forecasting, precipitation nowcasting, spatio-temporal analysis, and missing data reconstruction. Finally, current limitations and proposed workable solutions related to the use of DL for SITS prediction are also highlighted. [ABSTRACT FROM AUTHOR]

The availability of freshwater is becoming a global concern. Because agricultural consumption has been increasing steadily, the mapping of irrigated areas is key for supporting the monitoring of land use and better management of available water resources. In this paper, we propose a method to automatically detect and map center pivot irrigation systems using U-Net, an image segmentation convolutional neural network architecture, applied to a constellation of PlanetScope images from the Cerrado biome of Brazil. Our objective is to provide a fast and accurate alternative to map center pivot irrigation systems with very high spatial and temporal resolution imagery. We implemented a modified U-Net architecture using the TensorFlow library and trained it on the Google cloud platform with a dataset built from more than 42,000 very high spatial resolution PlanetScope images acquired between August 2017 and November 2018. The U-Net implementation achieved a precision of 99% and a recall of 88% to detect and map center pivot irrigation systems in our study area. This method, proposed to detect and map center pivot irrigation systems, has the potential to be scaled to larger areas and improve the monitoring of freshwater use by agricultural activities. [ABSTRACT FROM AUTHOR]

Surface ocean dynamics play a key role in the Earth system, contributing to regulate its climate and affecting the marine ecosystem functioning. Dynamical processes occur and interact in the upper ocean at multiple scales, down to, or even less than, few kilometres. These scales are not adequately resolved by present observing systems, and, in the last decades, global monitoring of surface currents has been based on the application of geostrophic balance to absolute dynamic topography maps obtained through the statistical interpolation of along-track satellite altimeter data. Due to the cross-track distance and repetitiveness of satellite acquisitions, the effective resolution of interpolated data is limited to several tens of kilometres. At the kilometre scale, sea surface temperature pattern evolution is dominated by advection, providing indirect information on upper ocean currents. Computer vision techniques are perfect candidates to infer this dynamical information from the combination of altimeter data, surface temperature images and observing-system geometry. Here, we exploit one class of image processing techniques, super-resolution, to develop an original neural-network architecture specifically designed to improve absolute dynamic topography reconstruction. Our model is first trained on synthetic observations built from a numerical general-circulation model and then tested on real satellite products. Provided concurrent clear-sky thermal observations are available, it proves able to compensate for altimeter sampling/interpolation limitations by learning from primitive equation data. The algorithm can be adapted to learn directly from future surface topography, and eventual surface currents, high-resolution satellite observations. [ABSTRACT FROM AUTHOR]

An efficient combination of remotely-sensed data and in situ measurements is needed to obtain accurate 3D ocean state estimates, representing a fundamental step to describe ocean dynamics and its role in the Earth climate system and marine ecosystems. Observations can either be assimilated in ocean general circulation models or used to feed data-driven reconstructions and diagnostic models. Here we describe an innovative deep learning algorithm that projects sea surface satellite data at depth after training with sparse co-located in situ vertical profiles. The technique is based on a stacked Long Short-Term Memory neural network, coupled to a Monte-Carlo dropout approach, and is applied here to the measurements collected between 2010 and 2018 over the North Atlantic Ocean. The model provides hydrographic vertical profiles and associated uncertainties from corresponding remotely sensed surface estimates, outperforming similar reconstructions from simpler statistical algorithms and feed-forward networks. [ABSTRACT FROM AUTHOR]

In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO). Nevertheless, the entry barriers for EO researchers are high due to the dense and rapidly developing field mainly driven by advances in computer vision (CV). To lower the barriers for researchers in EO, this review gives an overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN). The survey starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019. Thereby, we highlight the connections between the most important CNN architectures and cornerstones coming from CV in order to alleviate the evaluation of modern DL models. Furthermore, we briefly outline the evolution of the most popular DL frameworks and provide a summary of datasets in EO. By discussing well performing DL architectures on these datasets as well as reflecting on advances made in CV and their impact on future research in EO, we narrow the gap between the reviewed, theoretical concepts from CV and practical application in EO. [ABSTRACT FROM AUTHOR]