A field guide to cultivating computational biology

Evolving in sync with the computation revolution over the past 30 years, computational biology has emerged as a mature scientific field. While the field has made major contributions toward improving scientific knowledge and human health, individual computational biology practitioners at various institutions often languish in career development. As optimistic biologists passionate about the future of our field, we propose solutions for both eager and reluctant individual scientists, institutions, publishers, funding agencies, and educators to fully embrace computational biology. We believe that in order to pave the way for the next generation of discoveries, we need to improve recognition for computational biologists and better align pathways of career success with pathways of scientific progress. With 10 outlined steps, we call on all adjacent fields to move away from the traditional individual, single-discipline investigator research model and embrace multidisciplinary, data-driven, team science.

Participatory eco-landscape design: the case of NRIAG eco-park in Helwan, Egypt

As cities get more crowded and polluted, eco-landscape design gains increasing attention. Open spaces play a vital role in healing the natural environment as well as the physical and mental health of the citizens. This paper presents an exploratory eco-park design project in Helwan, Egypt. The project focuses on the opportunity of integrating marginalised natural environments, such as Wadis (dry streams), with the urban fabric through Eco-landscape design. The current work explores the complex environment, characterised by detailed multidisciplinary data, which requires multi-layer analysis. The discussion evaluates the tremendous effect of integrating the participatory qualitative method with other analytical and digital tools, such as modelling and Geographic Information Systems (GIS), to deduce scientific details and activities in the preliminary phases of zoning plans. This results in a constructive framework for merging these multi-methods and tools within the participatory eco-landscape design process. In addition, the conclusion highlights the peculiarity of the eco-landscape design and practice in the current Egyptian situation in a broad sense.

Machine Learning as a Service for DiSSCo’s Digital Specimen Architecture

International mass digitization efforts through infrastructures like the European Distributed System of Scientific Collections (DiSSCo), the US resource for Digitization of Biodiversity Collections (iDigBio), the National Specimen Information Infrastructure (NSII) of China, and Australia’s digitization of National Research Collections (NRCA Digital) make geo- and biodiversity specimen data freely, fully and directly accessible. Complementary, overarching infrastructure initiatives like the European Open Science Cloud (EOSC) were established to enable mutual integration, interoperability and reusability of multidisciplinary data streams including biodiversity, Earth system and life sciences (De Smedt et al. 2020). Natural Science Collections (NSC) are of particular importance for such multidisciplinary and internationally linked infrastructures, since they provide hard scientific evidence by allowing direct traceability of derived data (e.g., images, sequences, measurements) to physical specimens and material samples in NSC. To open up the large amounts of trait and habitat data and to link these data to digital resources like sequence databases (e.g., ENA), taxonomic infrastructures (e.g., GBIF) or environmental repositories (e.g., PANGAEA), proper annotation of specimen data with rich (meta)data early in the digitization process is required, next to bridging technologies to facilitate the reuse of these data. This was addressed in recent studies (Younis et al. 2018, Younis et al. 2020), where we employed computational image processing and artificial intelligence technologies (Deep Learning) for the classification and extraction of features like organs and morphological traits from digitized collection data (with a focus on herbarium sheets). However, such applications of artificial intelligence are rarely—this applies both for (sub-symbolic) machine learning and (symbolic) ontology-based annotations—integrated in the workflows of NSC’s management systems, which are the essential repositories for the aforementioned integration of data streams. This was the motivation for the development of a Deep Learning-based trait extraction and coherent Digital Specimen (DS) annotation service providing “Machine learning as a Service” (MLaaS) with a special focus on interoperability with the core services of DiSSCo, notably the DS Repository (nsidr.org) and the Specimen Data Refinery (Walton et al. 2020), as well as reusability within the data fabric of EOSC. Taking up the use case to detect and classify regions of interest (ROI) on herbarium scans, we demonstrate a MLaaS prototype for DiSSCo involving the digital object framework, Cordra, for the management of DS as well as instant annotation of digital objects with extracted trait features (and ROIs) based on the DS specification openDS (Islam et al. 2020). Source code available at: https://github.com/jgrieb/plant-detection-service

Explainable Machine Learning for Knee Osteoarthritis Diagnosis Based on a Novel Fuzzy Feature Selection Methodology

Knee Osteoarthritis (ΚΟΑ) is a degenerative joint disease of the knee that results from the progressive loss of cartilage. Due to KOA’s multifactorial nature and the poor understanding of its pathophysiology, there is a need for reliable tools that will reduce diagnostic errors made by clinicians. The existence of public databases has facilitated the advent of advanced analytics in KOA research however the heterogeneity of the available data along with the observed high feature dimensionality make this diagnosis task difficult. The objective of the present study is to provide a robust Feature Selection (FS) methodology that could: (i) handle the multidimensional nature of the available datasets and (ii) alleviate the defectiveness of existing feature selection techniques towards the identification of important risk factors which contribute to KOA diagnosis. For this aim, we used multidisciplinary data obtained from the Osteoarthritis Initiative database for individuals without or with KOA. The proposed fuzzy ensemble feature selection methodology aggregates the results of several FS algorithms (filter, wrapper and embedded ones) based on fuzzy logic. The effectiveness of the proposed methodology was evaluated using an extensive experimental setup that involved multiple competing FS algorithms and several well-known ML models. A 73.55 % classification accuracy was achieved by the best performing model (Random Forest classifier) on a group of twenty-one selected risk factors. Explainability analysis was finally performed to quantify the impact of the selected features on the model’s output thus enhancing our understanding of the rationale behind the decision-making mechanism of the best model.

An Approach to Estimating Reserve Volumes by Discounting Unauthorized Production Via Crude Oil Theft

Reserves are typically estimated and re-validated throughout the life of a producing field. The accuracy of this estimation is based on the availability of relevant and current data from that reservoir or field and other factors. There are several methods for estimating reserves, but the choice of which method is to be applied is often based on the data available per time. However, these methods are known to be associated with varying degrees of uncertainties arising from quality of data, the assumptions adopted and the experience of the evaluator. The biggest uncertainty in reserve estimation lies in the inability of the commonly available methods to estimate and discount the huge volumes lost due to unauthorized production by third parties, through crude oil theft, illegal bunkering activities, and spills. This leads to the gross overestimation of reserves and the economic viability of an asset, especially in onshore and shallow offshore assets where such illegal activities are typical and rampant. This paper showcases an approach of estimating reserves, through the integration of multidisciplinary data, which enables the estimation and discounting of crude oil volumes lost due to illegal production from a reservoir.

Satellite Radar Interferometry on corner reflectors in the area of mining region in Poland

<p>The EPOS-PL project is the Polish realization of the European Plate Observing System (EPOS) initiative, which aims at the integration of existing and newly created research infrastructures to facilitate the use of multidisciplinary data and products in the field of Earth sciences in Europe. Within the EPOS, one of the tasks aims at SAR data utilization for deformation monitoring in the area of Rydułtowy mine. The Rydułtowy mine is the oldest active mining in the Upper Silesia Coal Basin in Poland. In the area of this mine, five Corner Reflectors (CRs) have been deployed in the framework of the EPOS- PL. Additionally, in the area of interest one high-frequency GNSS receiver working permanently has been placed. This GNSS permanent station (RES100POL) enables estimating of deformation time-series based on multi-GNSS observation in post-processing.</p><p>In this study, we use Sentinel-1A/B TOPSAR images acquired between 25 June 2018 and 14 July 2019 in one ascending and two descending geometries with revisiting time of 6-days. Additionally, we use ground truths of two leveling and GNSS measurement campaigns carried out to precisely estimate deformations on five CRs (2<sup>nd</sup>-4<sup>th</sup> of July 2018 and 28<sup>th</sup>-30<sup>th</sup> of June 2019). GNSS static measurements were carried out via three independent measurement sessions. Coordinates of the station RES100POL and static GNSS and leveling measurements ware were used for validation of SAR measurements.</p><p>SAR data has been processed by means of classical consecutive Differential Interferometry (DInSAR) as well as Persistent Scattering (PSInSAR) approach. During SAR data processing, snow coverage accumulated on the CRs caused that some Sentinel-1 images from the winter season have been removed from DInSAR as well as PSInSAR processing. Results from ascending and descending orbits allow the estimation of vertical as well as east-west deformation components. Root Mean Square Error (RMSE) between CRs measured by conventional geodetic techniques and DInSAR was estimated as 31mm and 38mm for east-west and vertical deformation components, respectively. RMSE measured between PSInSAR and GNSS was estimated as 5mm and 7mm for east-west and vertical components, respectively. RMSE of 15mm and 3mm was estimated for DInSAR with respect to GNSS from RES100POL station for east-west and vertical components, respectively. Subsequently, RMSE of 4mm and 5mm was estimated as deformation time variations between PSInSAR and GNSS from RES1 station for east-west and vertical components, respectively. These measures indicate clearly the advantage of the PSInSAR method. However,  the PSInSAR approach was able to estimate deformations only for three CRs due to the fast and non-linear deformation pattern observed on other two CRs.</p>

Volcanic Tremor and its Relation to Volcano- and Glacier-related Processes

<p>Volcanic eruptions can affect the climate system, the environment and society. On ice covered volcanoes this threat intensifies due to the increasing explosivity in contact with water. Monitoring and early-warning of such eruptions is closely linked to real-time, multidisciplinary data analysis. This builds on a good understanding and location of the recorded signals.</p><p>I will summarize my work on understanding and modelling volcanic tremor, a long-lasting seismic signal with emergent onset. This tremor accompanies various volcano- and glacier-related processes and has to be reliably detected and distinguished from other sources. My examples range from modelling pre-eruptive subglacial tremor and silent magma flow, to monitoring eruptive tremor, to early warning of subglacial flooding, to hydrothermal explosions and boiling and other sources such as helicopters. These results are based on array analysis, amplitude location techniques and single-station arrays but I will also risk a look into the future embracing the emerging field of rotational seismology which might solve some challenges we face in volcanic and glacial environments and advance our understanding and modelling of volcanic signals at remote sites.</p>