Using data-driven algorithms for semi-automated geomorphological mapping

AbstractIn this paper, we compare the performance of two data-driven algorithms to deal with an automatic classification problem in geomorphology: Direct Sampling (DS) and Random Forest (RF). The main goal is to provide a semi-automated procedure for the geomorphological mapping of alpine environments, using a manually mapped zone as training dataset and predictor variables to infer the classification of a target zone. The applicability of DS to geomorphological classification was never investigated before. Instead, RF based classification has already been applied in few studies, but only with a limited number of geomorphological classes. The outcomes of both approaches are validated by comparing the eight detected classes with a geomorphological map elaborated on the field and considered as ground truth. Both DS and RF give satisfactory results and provide similar performances in term of accuracy and Cohen’s Kappa values. The map obtained with RF presents a noisier spatial distribution of classes than when using DS, because DS takes into account the spatial dependence of the different classes. Results suggest that DS and RF are both suitable techniques for the semi-automated geomorphological mapping in alpine environments at regional scale, opening the way for further improvements.

Download Full-text

Atmospheric CO2 inversions on the mesoscale using data-driven prior uncertainties: quantification of the European terrestrial CO2 fluxes

Atmospheric Chemistry and Physics ◽

10.5194/acp-18-3047-2018 ◽

2018 ◽

Vol 18 (4) ◽

pp. 3047-3064 ◽

Cited By ~ 9

Author(s):

Panagiotis Kountouris ◽

Christoph Gerbig ◽

Christian Rödenbeck ◽

Ute Karstens ◽

Thomas F. Koch ◽

...

Keyword(s):

Spatial Representation ◽

A Priori ◽

Regional Scale ◽

Data Driven ◽

Biogenic Carbon ◽

Sensitivity Tests ◽

Uncertainty Estimates ◽

Using Data ◽

A Priori Uncertainty ◽

Photosynthesis And Respiration

Abstract. Optimized biogenic carbon fluxes for Europe were estimated from high-resolution regional-scale inversions, utilizing atmospheric CO2 measurements at 16 stations for the year 2007. Additional sensitivity tests with different data-driven error structures were performed. As the atmospheric network is rather sparse and consequently contains large spatial gaps, we use a priori biospheric fluxes to further constrain the inversions. The biospheric fluxes were simulated by the Vegetation Photosynthesis and Respiration Model (VPRM) at a resolution of 0.1° and optimized against eddy covariance data. Overall we estimate an a priori uncertainty of 0.54 GtC yr−1 related to the poor spatial representation between the biospheric model and the ecosystem sites. The sink estimated from the atmospheric inversions for the area of Europe (as represented in the model domain) ranges between 0.23 and 0.38 GtC yr−1 (0.39 and 0.71 GtC yr−1 up-scaled to geographical Europe). This is within the range of posterior flux uncertainty estimates of previous studies using ground-based observations.

Download Full-text

Atmospheric CO2 inversions at the mesoscale using data driven prior uncertainties. Part2: the European terrestrial CO2 fluxes

10.5194/acp-2016-578 ◽

2016 ◽

Author(s):

Panagiotis Kountouris ◽

Christoph Gerbig ◽

Christian Rödenbeck ◽

Ute Karstens ◽

Thomas F. Koch ◽

...

Keyword(s):

Spatial Representation ◽

A Priori ◽

Regional Scale ◽

Data Driven ◽

Biogenic Carbon ◽

Sensitivity Tests ◽

Uncertainty Estimates ◽

Using Data ◽

A Priori Uncertainty ◽

Photosynthesis And Respiration

Abstract. Optimized biogenic carbon fluxes for Europe were estimated from high resolution regional scale inversions, utilizing atmospheric CO2 measurements at 16 stations for the year 2007. Additional sensitivity tests with different data-driven error structures were performed. As the atmospheric network is rather sparse and consequently contains large spatial gaps, we use a priori biospheric fluxes to further constrain the inversions. The biospheric fluxes were simulated by the Vegetation Photosynthesis and Respiration Model (VPRM) at a resolution of 0.1° and optimized against Eddy covariance data. Overall we estimate an a priori uncertainty of 0.54 GtC y−1 related to the poor spatial representation between the biospheric model and the ecosystem sites. The sink estimated from the atmospheric inversions for the area of Europe (as represented in the model domain) ranges between 0.23 and 0.38 GtC y−1 (0.30 and 0.49 GtC y−1 up-scaled to geographical Europe). This is within the range of posterior flux uncertainty estimates of previous studies using ground based observations.

Download Full-text

Mammogram Segmentation using Multi-atlas Deformable Registration

10.1101/542217 ◽

2019 ◽

Author(s):

Manish Kumar Sharma ◽

Mainak Jas ◽

Vikrant Karale ◽

Anup Sadhu ◽

Sudipta Mukhopadhyay

Keyword(s):

Ground Truth ◽

Data Driven ◽

Second Phase ◽

Morphological Operations ◽

Region Segmentation ◽

Expert Radiologist ◽

Candidate Image ◽

Combining Data ◽

Using Data ◽

Automated Algorithms

Accurate breast region segmentation is an important step in various automated algorithms involving detection of lesions like masses and microcalcifications, and efficient telemammography. Existing segmentation algorithms underperform due to variations in image quality and shape of the breast region. In this paper, we propose to segment breast region by combining data-driven clustering with deformable image registration. In the first phase of the approach, we identify atlas images from a dataset of mammograms using data-driven clustering. Then, we segment these atlas images and use in the next phase of the algorithm. The second phase is atlas-based registration. For a candidate image, we find the most similar atlas image from the set of atlases identified in phase one. We deform the selected atlas image to match the given test image using the Demon's registration algorithm. Then, the segmentation mask of the deformed atlas is transferred to the mammogram in consideration. Finally, we refine the segmentation mask with some morphological operations in order to obtain accurate breast region boundary. We evaluated the performance of our method using ground-truth segmentation masks verified by an expert radiologist. We compared the proposed method with three existing state-of-the-art algorithms for breast region segmentation and the proposed approach outperformed all three in most of the cases.

Download Full-text

A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w14-255-2019 ◽

2019 ◽

Vol XLII-4/W14 ◽

pp. 255-260

Author(s):

M. A. Zurbaran ◽

P. Wightman ◽

M. A. Brovelli

Keyword(s):

Machine Learning ◽

Satellite Imagery ◽

Binary Classification ◽

Ground Truth ◽

Classification Problem ◽

Training Dataset ◽

Road Detection ◽

Area Of Interest ◽

Desirable Outcome ◽

Public Datasets

Abstract. Satellite imagery from earth observation missions enable processing big data to gather information about the world. Automatizing the creation of maps that reflect ground truth is a desirable outcome that would aid decision makers to take adequate actions in alignment with the United Nations Sustainable Development Goals. In order to harness the power that the availability of the new generation of satellites enable, it is necessary to implement techniques capable of handling annotations for the massive volume and variability of high spatial resolution imagery for further processing. However, the availability of public datasets for training machine learning models for image segmentation plays an important role for scalability.This work focuses on bridging remote sensing and computer vision by providing an open source based pipeline for generating machine learning training datasets for road detection in an area of interest. The proposed pipeline addresses road detection as a binary classification problem using road annotations existing in OpenStreetMap for creating masks. For this case study, Planet images of 3m resolution are used for creating a training dataset for road detection in Kenya.

Download Full-text

Imbalanced Classification Problem Using Data-driven and Random Forest Method

Proceedings of the 3rd International Conference on Data Science and Information Technology ◽

10.1145/3414274.3414278 ◽

2020 ◽

Author(s):

Wan Wang ◽

Xinglu Liu ◽

Wai Kin Victor Chan

Keyword(s):

Random Forest ◽

Classification Problem ◽

Data Driven ◽

Imbalanced Classification ◽

Random Forest Method ◽

Using Data

Download Full-text

Towards TBM Automation: On-The-Fly Characterization and Classification of Ground Conditions Ahead of a TBM Using Data-Driven Approach

Applied Sciences ◽

10.3390/app11031060 ◽

2021 ◽

Vol 11 (3) ◽

pp. 1060

Author(s):

Sylvanus Sebbeh-Newton ◽

Prosper E.A. Ayawah ◽

Jessica W.A. Azure ◽

Azupuri G.A. Kaba ◽

Fauziah Ahmad ◽

...

Keyword(s):

Rock Mass ◽

Tunnel Boring Machine ◽

Rock Mass Classification ◽

Data Driven ◽

Training Dataset ◽

Ground Conditions ◽

Data Driven Approach ◽

Mass Classification ◽

Using Data

Pre-tunneling exploration for rock mass classification is a common practice in tunneling projects. This study proposes a data-driven approach that allows for rock mass classification. Two machine learning (ML) classification models, namely random forest (RF) and extremely randomized tree (ERT), are employed to classify the rock mass conditions encountered in the Pahang-Selangor Raw Water Tunnel in Malaysia using tunnel boring machine (TBM) operating parameters. Due to imbalance of rock classes distribution, an oversampling technique was used to obtain a balanced training dataset for unbiased learning of the ML models. A five-fold cross-validation approach was used to tune the model hyperparameters and validation-set approach was used for the model evaluation. ERT achieved an overall accuracy of 95%, while RF achieved 94% accuracy, in rightly classifying rock mass conditions. The result shows that the proposed approach has the potential to identify and correctly classify ground conditions of a TBM, which allows for early problem detection and on-the-fly support system selection based on the identified ground condition. This study, which is part of an ongoing effort towards developing reliable models that could be incorporated into TBMs, shows the potential of data-driven approaches for on-the-fly classification of ground conditions ahead of a TBM and could allow for the early detection of potential construction problems.

Download Full-text