scholarly journals Assessing the Prediction Accuracy of Geomorphon-Based Automated Landform Classification: An Example from the Ionian Coastal Belt of Southern Italy

2021 ◽  
Vol 10 (11) ◽  
pp. 725
Author(s):  
Dario Gioia ◽  
Maria Danese ◽  
Giuseppe Corrado ◽  
Paola Di Leo ◽  
Antonio Minervino Amodio ◽  
...  
Keyword(s):  
Prediction Accuracy ◽  
Large Scale ◽  
Research Field ◽  
Plain Area ◽  
Geomorphological Mapping ◽  
Fluvial Terraces ◽  
Landform Classification ◽  
Coastal Belt ◽  
Genetic Interpretation ◽  
Large Sector

Automatic procedures for landform extraction is a growing research field but extensive quantitative studies of the prediction accuracy of Automatic Landform Classification (ACL) based on a direct comparison with geomorphological maps are rather limited. In this work, we test the accuracy of an algorithm of automatic landform classification on a large sector of the Ionian coast of the southern Italian belt through a quantitative comparison with a detailed geomorphological map. Automatic landform classification was performed by using an algorithm based on the individuation of basic landform classes named geomorphons. Spatial overlay between the main mapped landforms deriving from traditional geomorphological analysis and the automatic landform classification results highlighted a satisfactory percentage of accuracy (higher than 70%) of the geomorphon-based method for the coastal plain area and drainage network. The percentage of accuracy decreased by about 20–30% for marine and fluvial terraces, while the overall accuracy of the ACL map is 69%. Our results suggest that geomorphon-based classification could represent a basic and robust tool to recognize the main geomorphological elements of landscape at a large scale, which can be useful for the advanced steps of geomorphological mapping such as genetic interpretation of landforms and detailed delineation of complex and composite geomorphic elements.

scholarly journals Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

2021 ◽  
Vol 13 (16) ◽  
pp. 3065
Author(s):  
Libo Wang ◽  
Rui Li ◽  
Dongzhi Wang ◽  
Chenxi Duan ◽  
Teng Wang ◽  
...  
Keyword(s):  
Large Scale ◽  
Texture Features ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Research Field ◽  
Learning Approaches ◽  
Fine Grained ◽  
Urban Scene ◽  
Fine Resolution ◽  
With Memory

Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. In addition, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset.

scholarly journals Geomorphological and Geochronological Analysis Applied to the Quaternary Landscape Evolution of the Yeltes River (Salamanca, Spain)

2020 ◽  
Vol 12 (19) ◽  
pp. 7869 ◽  
Author(s):  
Iván Martín-Martín ◽  
Pablo-Gabriel Silva ◽  
Antonio Martínez-Graña ◽  
Javier Elez
Keyword(s):  
Transfer Functions ◽  
Sedimentary Basins ◽  
Central Spain ◽  
Geomorphological Mapping ◽  
Fluvial Terraces ◽  
Digital Elevation ◽  
Late Neogene ◽  
Climate Evolution ◽  
Reported Data ◽  
Geomorphological Evolution

This paper aims to study the Quaternary geomorphological evolution of the Yeltes river-valley (Duero Basin, Central Spain) primarily based on the study of the Late Neogene piedmont dissected by the river and its Quaternary terrace sequence, since fluvial terraces are excellent archives to study the landscape and climate evolution during this period. Detailed geomorphological mapping implemented in GIS-based digital elevation models was used to the further applications of existing fluvial chronofunctions (relative terrace height-age transfer functions) to establish a numerical geochronology to the sequence of fluvial terraces in the zone. The obtained theoretical ages points to an onset of fluvial incision in the zone after 2.0–2.5 Myr ago, with the dissection of the “Raña surface” (a Gelasian alluvial piedmont widely developed in Central Spain). The obtained terrace ages coincide, in most cases, with warm isotopic stages (MIS) or mainly with the transit of cold to warm MIS. Additionally, this study suggests that the full connectivity of the Yeltes drainage (Ciudad Rodrigo Basin) with the Atlantic drainage was not completely effective until MIS 9 (c. 0.29 Myr). The new reported data allows for the exploration of the timing and processes involved in the capture of inland sedimentary basins (Ciudad Rodrigo, Duero basins) by the Atlantic drainage during the early Quaternary.

Open source riverscapes: Analyzing the river corridor of the Naryn River in Kyrgyzstan based on open access data

2021 ◽  
Author(s):  
Florian Betz ◽  
Magdalena Lauermann ◽  
Bernd Cyffka
Keyword(s):  
Remote Sensing ◽  
Open Access ◽  
Large Scale ◽  
Data Sets ◽  
Hierarchical Systems ◽  
Geomorphological Mapping ◽  
Open Access Data ◽  
Access Data ◽  
River Corridors ◽  
River Corridor

<p>In fluvial geomorphology as well as in freshwater ecology, rivers are commonly seen as nested hierarchical systems functioning over a range of spatial and temporal scales. Thus, for a comprehensive assessment, information on various scales is required. Over the past decade, remote sensing based approaches have become increasingly popular in river science to increase the spatial scale of analysis. However, data-scarce areas have been mostly ignored so far despite the fact that most remaining free flowing – and thus ecologically valuable – rivers worldwide are located in regions characterized by a lack of data sources like LiDAR or even aerial imagery. High resolution satellite data would be able to fill this data gap, but tends to be too costly for large scale applications what limits the ability for comprehensive studies on river systems in such remote areas. This in turn is a limitation for management and conservation of these rivers.</p><p>In this contribution, we suggest an approach for river corridor mapping based on open access data only in order to foster large scale geomorphological mapping of river corridors in data-scarce areas. For this aim, we combine advanced terrain analysis with multispectral remote sensing using the SRTM-1 DEM along with Landsat OLI imagery. We take the Naryn River in Kyrgyzstan as an example to demonstrate the potential of these open access data sets to derive a comprehensive set of parameters for characterizing this river corridor. The methods are adapted to the specific characteristics of medium resolution open access data sets and include an innovative, fuzzy logic based approach for riparian zone delineation, longitudinal profile smoothing based on constrained quantile regression and a delineation of the active channel width as needed for specific stream power computation. In addition, an indicator for river dynamics based on Landsat time series is developed. For each derived river corridor parameter, a rigor validation is performed. The results demonstrate, that our open access approach for geomorphological mapping of river corridors is capable to provide results sufficiently accurate to derive reach averaged information. Thus, it is well suited for large scale river characterization in data-scarce regions where otherwise the river corridors would remain largely unexplored from an up-to-date riverscape perspective. Such a characterization might be an entry point for further, more detailed research in selected study reaches and can deliver the required comprehensive background information for a range of topics in river science.</p>

Skill assessment of post-processing methods for ECMWF SEAS5 seasonal forecasts over Europe

2021 ◽  
Author(s):  
Alice Crespi ◽  
Marcello Petitta ◽  
Lucas Grigis ◽  
Paola Marson ◽  
Jean-Michel Soubeyroux ◽  
...  
Keyword(s):  
Large Scale ◽  
Production Management ◽  
Spatial Scales ◽  
Research Field ◽  
Skill Assessment ◽  
Post Processing ◽  
Seasonal Forecasts ◽  
Climate Services ◽  
Local Climate ◽  
Climate Conditions

<p>Seasonal forecasts provide information on climate conditions several months ahead and therefore they could represent a valuable support for decision making, warning systems as well as for the optimization of industry and energy sectors. However, forecast systems can be affected by systematic biases and have horizontal resolutions which are typically coarser than the spatial scales of the practical applications. For this reason, the reliability of forecasts needs to be carefully assessed before applying and interpreting them for specific applications. In addition, the use of post-processing approaches is recommended in order to improve the representativeness of the large-scale predictions of regional and local climate conditions. The development and evaluation downscaling and bias-correction procedures aiming at improving the skills of the forecasts and the quality of derived climate services is currently an open research field. In this context, we evaluated the skills of ECMWF SEAS5 forecasts of monthly mean temperature, total precipitation and wind speed over Europe and we assessed the skill improvements of calibrated predictions.</p><p>For the calibration, we combined a bilinear interpolation and a quantile mapping approach to obtain corrected monthly forecasts on a 0.25°x0.25° grid from the original 1°x1° values. The forecasts were corrected against the reference ERA5 reanalysis over the hindcast period 1993–2016. The processed forecasts were compared over the same domain and period with another calibrated set of ECMWF SEAS5 forecasts obtained by the ADAMONT statistical method.</p><p>The skill assessment was performed by means of both deterministic and probabilistic verification metrics evaluated over seasonal forecasted aggregations for the first lead time. Greater skills of the forecast systems in Europe were generally observed in spring and summer, especially for temperature, with a spatial distribution varying with the seasons. The calibration was proved to effectively correct the model biases for all variables, however the metrics not accounting for bias did not show significant improvements in most cases, and in some areas and seasons even small degradations in skills were observed.</p><p>The presented study supported the activities of the H2020 European project SECLI-FIRM on the improvement of the seasonal forecast applicability for energy production, management and assessment.</p>

scholarly journals KK-DBP: A Multi-Feature Fusion Method for DNA-Binding Protein Identification Based on Random Forest

2021 ◽  
Vol 12 ◽  
Author(s):  
Yuran Jia ◽  
Shan Huang ◽  
Tianjiao Zhang
Keyword(s):  
Dna Binding ◽  
Prediction Accuracy ◽  
Large Scale ◽  
Protein Identification ◽  
Feature Fusion ◽  
Binding Protein ◽  
Rapid Development ◽  
Dna Binding Protein ◽  
Feature Extraction Method ◽  
Independent Test Dataset

DNA-binding protein (DBP) is a protein with a special DNA binding domain that is associated with many important molecular biological mechanisms. Rapid development of computational methods has made it possible to predict DBP on a large scale; however, existing methods do not fully integrate DBP-related features, resulting in rough prediction results. In this article, we develop a DNA-binding protein identification method called KK-DBP. To improve prediction accuracy, we propose a feature extraction method that fuses multiple PSSM features. The experimental results show a prediction accuracy on the independent test dataset PDB186 of 81.22%, which is the highest of all existing methods.

scholarly journals Geomorphological mapping based on DEMs and GIS: A review

2019 ◽  
Vol 1 ◽  
pp. 1-1
Author(s):  
Takashi Oguchi
Keyword(s):  
Remote Sensing ◽  
Laser Scanning ◽  
Aerial Photographs ◽  
Topographic Maps ◽  
Formation Processes ◽  
Geomorphological Mapping ◽  
Topographic Data ◽  
Aerial Photogrammetry ◽  
Landform Classification ◽  
Shape Characteristics

<p><strong>Abstract.</strong> Geomorphology is a scientific discipline dealing with the characteristics, origin, and evolution of landforms. It utilizes topographic data such as spot height information, contour lines on topographic maps, and DEMs (Digital Elevation Models). Topographic data were traditionally obtained by ground surveying, but introduction of aerial photogrammetry in the early 20th century enabled more efficient data acquisition based on remote sensing. In recent years, active remote sensing methods including airborne and terrestrial laser scanning and applications of satellite radar have also been employed, and aerial photogrammetry has become easier and popular thanks to drones and a new photogrammetric method, SfM (Structure from Motion). The resultant topographic data especially raster DEMs are combined with GIS (Geographic Information Systems) to obtain derivatives such as slope and aspect as well as to conduct efficient geomorphological mapping. Resultant maps can depict various topographic characteristics based on surface height and DEM derivatives, and applications of advanced algorithms and some heuristic reasoning permit semi-automated landform classification. This quantitative approach differs from traditional and more qualitative methods to produce landform classification maps using visual interpretation of analogue aerial photographs and topographic maps as well as field observations.</p><p>For scientific purposes, landforms need to be classified based on not only shape characteristics but also formation processes and ages. Among them, DEMs only represent shape characteristics, and understanding formation processes and ages usually require other data such as properties of surficial deposits observed in the field. However, numerous geomorphological studies indicate relationships between shapes and forming-processes of landforms, and even ages of landforms affect shapes such as a wider distribution of dissected elements within older landforms. Recent introduction of artificial intelligence in geomorphology including machine learning and deep learning may permit us to better understand the relationships of shapes with processes and ages. Establishing such relationships, however, is still highly challenging, and at this moment most geomorphologists think landform classification maps based on the traditional methods are more usable than those from the DEM-based methods. Nevertheless, researchers of some other fields such as civil engineering more appreciate the DEM-based methods because they can be conducted without deep geomorphological knowledge. Therefore, the methods should be developed for interdisciplinary understanding. This paper reviews and discusses such complex situations of geomorphological mapping today in relation to historical development of methodology.</p>

scholarly journals A billion synthetic 3D-antibody-antigen complexes enable unconstrained machine-learning formalized investigation of antibody specificity prediction

2021 ◽  
Author(s):  
Philippe Auguste Robert ◽  
Rahmad Akbar ◽  
Robert Frank ◽  
Milena Pavlović ◽  
Michael Widrich ◽  
...  
Keyword(s):  
Machine Learning ◽  
In Silico ◽  
Prediction Accuracy ◽  
Large Scale ◽  
Structural Information ◽  
Antigen Binding ◽  
Antibody Specificity ◽  
Binding Prediction ◽  
Information Encoding ◽  
Prediction Problems

Machine learning (ML) is a key technology to enable accurate prediction of antibody-antigen binding, a prerequisite for in silico vaccine and antibody design. Two orthogonal problems hinder the current application of ML to antibody-specificity prediction and the benchmarking thereof: (i) The lack of a unified formalized mapping of immunological antibody specificity prediction problems into ML notation and (ii) the unavailability of large-scale training datasets. Here, we developed the Absolut! software suite that allows the parameter-based unconstrained generation of synthetic lattice-based 3D-antibody-antigen binding structures with ground-truth access to conformational paratope, epitope, and affinity. We show that Absolut!-generated datasets recapitulate critical biological sequence and structural features that render antibody-antigen binding prediction challenging. To demonstrate the immediate, high-throughput, and large-scale applicability of Absolut!, we have created an online database of 1 billion antibody-antigen structures, the extension of which is only constrained by moderate computational resources. We translated immunological antibody specificity prediction problems into ML tasks and used our database to investigate paratope-epitope binding prediction accuracy as a function of structural information encoding, dataset size, and ML method, which is unfeasible with existing experimental data. Furthermore, we found that in silico investigated conditions, predicted to increase antibody specificity prediction accuracy, align with and extend conclusions drawn from experimental antibody-antigen structural data. In summary, the Absolut! framework enables the development and benchmarking of ML strategies for biotherapeutics discovery and design.

scholarly journals End-to-End Transition-Based Online Dialogue Disentanglement

2020 ◽  
Author(s):  
Hui Liu ◽  
Zhan Shi ◽  
Jia-Chen Gu ◽  
Quan Liu ◽  
Si Wei ◽  
...  
Keyword(s):  
Large Scale ◽  
Online Algorithm ◽  
Research Field ◽  
Semantic Coherence ◽  
Large Scale Dataset ◽  
End To End ◽  
Sequential Information ◽  
Almost All ◽  
Classification And Clustering ◽  
Sequential Semantics

Dialogue disentanglement aims to separate intermingled messages into detached sessions. The existing research focuses on two-step architectures, in which a model first retrieves the relationships between two messages and then divides the message stream into separate clusters. Almost all existing work puts significant efforts on selecting features for message-pair classification and clustering, while ignoring the semantic coherence within each session. In this paper, we introduce the first end-to- end transition-based model for online dialogue disentanglement. Our model captures the sequential information of each session as the online algorithm proceeds on processing a dialogue. The coherence in a session is hence modeled when messages are sequentially added into their best-matching sessions. Meanwhile, the research field still lacks data for studying end-to-end dialogue disentanglement, so we construct a large-scale dataset by extracting coherent dialogues from online movie scripts. We evaluate our model on both the dataset we developed and the publicly available Ubuntu IRC dataset [Kummerfeld et al., 2019]. The results show that our model significantly outperforms the existing algorithms. Further experiments demonstrate that our model better captures the sequential semantics and obtains more coherent disentangled sessions.

scholarly journals The role of airborne volcanic ash for the surface ocean biogeochemical iron-cycle: a review

2009 ◽  
Vol 6 (4) ◽  
pp. 6441-6489 ◽  
Author(s):  
S. Duggen ◽  
N. Olgun ◽  
P. Croot ◽  
L. Hoffmann ◽  
H. Dietze ◽  
...  
Keyword(s):  
Large Scale ◽  
Volcanic Ash ◽  
Volcanic Eruptions ◽  
Research Field ◽  
Ash Deposition ◽  
Future Directions ◽  
Iron Cycle ◽  
Surface Ocean ◽  
Wide Range

Abstract. Iron is a key micronutrient for phytoplankton growth in the surface ocean. Yet the significance of volcanism for the marine biogeochemical iron-cycle is poorly constrained. Recent studies, however, suggest that offshore deposition of airborne ash from volcanic eruptions is a way to inject significant amounts of bio-available iron into the surface ocean. Volcanic ash may be transported up to several tens of kilometres high into the atmosphere during large-scale eruptions and fine ash may encircle the globe for years, thereby reaching even the remotest and most iron-starved oceanic areas. Scientific ocean drilling demonstrates that volcanic ash layers and dispersed ash particles are frequently found in marine sediments and that therefore volcanic ash deposition and iron-injection into the oceans took place throughout much of the Earth's history. The data from geochemical and biological experiments, natural evidence and satellite techniques now available suggest that volcanic ash is a so far underestimated source for iron in the surface ocean, possibly of similar importance as aeolian dust. Here we summarise the development of and the knowledge in this fairly young research field. The paper covers a wide range of chemical and biological issues and we make recommendations for future directions in these areas. The review paper may thus be helpful to improve our understanding of the role of volcanic ash for the marine biogeochemical iron-cycle, marine primary productivity and the ocean-atmosphere exchange of CO2 and other gases relevant for climate throughout the Earth's history.

Sign in / Sign up

Export Citation Format

Share Document