Refine
Has Fulltext
- yes (26)
Is part of the Bibliography
- yes (26)
Year of publication
- 2020 (26) (remove)
Document Type
- Journal article (23)
- Doctoral Thesis (3)
Language
- English (26) (remove)
Keywords
- machine learning (4)
- remote sensing (4)
- AI (2)
- CNN (2)
- Earth Observation (2)
- Earth observation (2)
- Landsat (2)
- SAR (2)
- artificial intelligence (2)
- convolutional neural networks (2)
Institute
- Institut für Geographie und Geologie (26) (remove)
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.
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.
Land surface temperature (LST) is a fundamental parameter within the system of the Earth’s surface and atmosphere, which can be used to describe the inherent physical processes of energy and water exchange. The need for LST has been increasingly recognised in agriculture, as it affects the growth phases of crops and crop yields. However, challenges in overcoming the large discrepancies between the retrieved LST and ground truth data still exist. Precise LST measurement depends mainly on accurately deriving the surface emissivity, which is very dynamic due to changing states of land cover and plant development. In this study, we present an LST retrieval algorithm for the combined use of multispectral optical and thermal UAV images, which has been optimised for operational applications in agriculture to map the heterogeneous and diverse agricultural crop systems of a research campus in Germany (April 2018). We constrain the emissivity using certain NDVI thresholds to distinguish different land surface types. The algorithm includes atmospheric corrections and environmental thermal emissions to minimise the uncertainties. In the analysis, we emphasise that the omission of crucial meteorological parameters and inaccurately determined emissivities can lead to a considerably underestimated LST; however, if the emissivity is underestimated, the LST can be overestimated. The retrieved LST is validated by reference temperatures from nearby ponds and weather stations. The validation of the thermal measurements indicates a mean absolute error of about 0.5 K. The novelty of the dual sensor system is that it simultaneously captures highly spatially resolved optical and thermal images, in order to construct the precise LST ortho-mosaics required to monitor plant diseases and drought stress and validate airborne and satellite data.
Forests in Germany cover around 11.4 million hectares and, thus, a share of 32% of Germany's surface area. Therefore, forests shape the character of the country's cultural landscape. Germany's forests fulfil a variety of functions for nature and society, and also play an important role in the context of climate levelling. Climate change, manifested via rising temperatures and current weather extremes, has a negative impact on the health and development of forests. Within the last five years, severe storms, extreme drought, and heat waves, and the subsequent mass reproduction of bark beetles have all seriously affected Germany’s forests. Facing the current dramatic extent of forest damage and the emerging long-term consequences, the effort to preserve forests in Germany, along with their diversity and productivity, is an indispensable task for the government. Several German ministries have and plan to initiate measures supporting forest health. Quantitative data is one means for sound decision-making to ensure the monitoring of the forest and to improve the monitoring of forest damage. In addition to existing forest monitoring systems, such as the federal forest inventory, the national crown condition survey, and the national forest soil inventory, systematic surveys of forest condition and vulnerability at the national scale can be expanded with the help of a satellite-based earth observation. In this review, we analysed and categorized all research studies published in the last 20 years that focus on the remote sensing of forests in Germany. For this study, 166 citation indexed research publications have been thoroughly analysed with respect to publication frequency, location of studies undertaken, spatial and temporal scale, coverage of the studies, satellite sensors employed, thematic foci of the studies, and overall outcomes, allowing us to identify major research and geoinformation product gaps.
Water crises are becoming severe in recent times, further fueled by population increase and climate change. They result in complex and unsustainable water management. Spatial estimation of consumptive water use is vital for performance assessment of the irrigation system using Remote Sensing (RS). For this study, its estimation is done using the Soil Energy Balance Algorithm for Land (SEBAL) approach. Performance indicators including equity, adequacy, and reliability were worked out at various spatiotemporal scales. Moreover, optimization and sustainable use of water resources are not possible without knowing the factors mainly influencing consumptive water use of major crops. For that purpose, random forest regression modelling was employed using various sets of factors for site-specific, proximity, and cropping system. The results show that the system is underperforming both for Kharif (i.e., summer) and Rabi (i.e., winter) seasons. Performance indicators highlight poor water distribution in the system, a shortage of water supply, and unreliability. The results are relatively good for Rabi as compared to Kharif, with an overall poor situation for both seasons. Factors importance varies for different crops. Overall, distance from canal, road density, canal density, and farm approachability are the most important factors for explaining consumptive water use. Auditing of consumptive water use shows the potential for resource optimization through on-farm water management by the targeted approach. The results are based on the present situation without considering future changes in canal water supply and consumptive water use under climate change.
Open Spaces in Alpine Countries: Analytical Concepts and Preservation Strategies in Spatial Planning
(2020)
Open spaces in the Alps are becoming noticeably scarcer, and the long-term consequences for humans and the environment are often overlooked. Open spaces preserve ecosystem services but are under pressure in many Alpine valleys due to demographic and economic development as well as corresponding technical and tourism infrastructure. This article conceptualizes and measures open spaces in Alpine environments. In addition to analyzing existing spatial planning instruments and the open spaces resulting from 2 of them-the Bavarian Alpenplan in Germany and the Tyrolean Ruhegebiete in Austria-we identify open spaces in Switzerland using a geographic information system. More generally, we discuss how spatial planning deals with open spaces. Results show that both the Alpenplan and the Ruhegebiete have contributed significantly to the protection of open spaces in the Bavarian and Tyrolean Alps since the 1970s. Indeed, both approaches prevented several development projects. In the Swiss Alps, open spaces cover 41.9% of the Alpine Convention area. A share of 40.3% vegetation-free open spaces shows that they are concentrated in high alpine areas. Of the open spaces identified, 64.6% are covered by protected areas. Hence, about one third of the open spaces still existing in the Swiss Alps need preservation, not only for ecological connectivity reasons but also to preserve them for generations to come. We conclude that different sectoral approaches for the conservation of open spaces for people and natural heritage in the Alps and other high mountain ranges should be better coordinated. In addition, much more intensive crossborder cooperation in spatial development and planning is needed to preserve open spaces throughout the Alpine arc.
A disease is non-communicable when it is not transferred from one person to another. Typical examples include all types of cancer, diabetes, stroke, or allergies, as well as mental diseases. Non-communicable diseases have at least two things in common — environmental impact and chronicity. These diseases are often associated with reduced quality of life, a higher rate of premature deaths, and negative impacts on a countries' economy due to healthcare costs and missing work force. Additionally, they affect the individual's immune system, which increases susceptibility toward communicable diseases, such as the flu or other viral and bacterial infections. Thus, mitigating the effects of non-communicable diseases is one of the most pressing issues of modern medicine, healthcare, and governments in general. Apart from the predisposition toward such diseases (the genome), their occurrence is associated with environmental parameters that people are exposed to (the exposome). Exposure to stressors such as bad air or water quality, noise, extreme heat, or an overall unnatural surrounding all impact the susceptibility to non-communicable diseases. In the identification of such environmental parameters, geoinformation products derived from Earth Observation data acquired by satellites play an increasingly important role. In this paper, we present a review on the joint use of Earth Observation data and public health data for research on non-communicable diseases. We analyzed 146 articles from peer-reviewed journals (Impact Factor ≥ 2) from all over the world that included Earth Observation data and public health data for their assessments. Our results show that this field of synergistic geohealth analyses is still relatively young, with most studies published within the last five years and within national boundaries. While the contribution of Earth Observation, and especially remote sensing-derived geoinformation products on land surface dynamics is on the rise, there is still a huge potential for transdisciplinary integration into studies. We see the necessity for future research and advocate for the increased incorporation of thematically profound remote sensing products with high spatial and temporal resolution into the mapping of exposomes and thus the vulnerability and resilience assessment of a population regarding non-communicable diseases.
Periglacial environments are facing dramatic changes. Warming air temperatures and strong snow cover variations fundamentally affect landforming processes in this hotspot region of Climate Change. But before we can assess the response of landform development to a changing climate, we need to enhance our understanding of the internal structure of those landforms. Within this study, a broad scope of landform types from alpine and subarctic regions is investigated: rock glaciers, solifluction lobes, palsas and patterned ground. By using the geophysical methods 2-D and 3-D ERI, as well as GPR surveying, structural differences and similarities between landform units of different or the same landform types are highlighted. This enables a reconstruction of their past and a projection of their future development.
Land cover is a key variable in monitoring applications and new processing technologies made deriving this information easier. Yet, classification algorithms remain dependent on samples collected on the field and field campaigns are limited by financial, infrastructural and political boundaries. Here, animal tracking data could be an asset. Looking at the land cover dependencies of animal behaviour, we can obtain land cover samples over places that are difficult to access. Following this premise, we evaluated the potential of animal movement data to map land cover. Specifically, we used 13 White Storks (Cicona cicona) individuals of the same population to map agriculture within three test regions distributed along their migratory track. The White Stork has adapted to foraging over agricultural lands, making it an ideal source of samples to map this land use. We applied a presence-absence modelling approach over a Normalized Difference Vegetation Index (NDVI) time series and validated our classifications, with high-resolution land cover information. Our results suggest White Stork movement is useful to map agriculture, however, we identified some limitations. We achieved high accuracies (F1-scores > 0.8) for two test regions, but observed poor results over one region. This can be explained by differences in land management practices. The animals preferred agriculture in every test region, but our data showed a biased distribution of training samples between irrigated and non-irrigated land. When both options occurred, the animals disregarded non-irrigated land leading to its misclassification as non-agriculture. Additionally, we found difference between the GPS observation dates and the harvest times for non-irrigated crops. Given the White Stork takes advantage of managed land to search for prey, the inactivity of these fields was the likely culprit of their underrepresentation. Including more species attracted to agriculture - with other land-use dependencies and observation times - can contribute to better results in similar applications.
The internal structures of a moraine complex mostly provide information about the manner in which they develop and thus they can transmit details about several processes long after they have taken place. While the occurrence of glacier–permafrost interactions during the formation of large thrust moraine complexes at polar and subpolar glaciers as well as at marginal positions of former ice sheets has been well understood, their role in the formation of moraines on comparatively small alpine glaciers is still very poorly investigated. Therefore, the question arises as to whether evidence of former glacier–permafrost interactions can still be found in glacier forefields of small alpine glaciers and to what extent these differ from the processes in finer materials at larger polar or subpolar glaciers. To investigate this, electrical resistivity tomography (ERT) and ground-penetrating radar (GPR) surveys were carried out in the area of a presumed alpine thrust moraine complex in order to investigate internal moraine structures. The ERT data confirmed the presence of a massive ice core within the central and proximal parts of the moraine complex. Using GPR, linear internal structures were detected, which were interpreted as internal shear planes due to their extent and orientation. These shear planes lead to the assumption that the moraine complex is of glaciotectonic origin. Based on the detected internal structures and the high electrical resistivity values, it must also be assumed that the massive ice core is of sedimentary or polygenetic origin. The combined approach of the two methods enabled the authors of this study to detect different internal structures and to deduce a conceptual model of the thrust moraine formation.