Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Feature Extraction”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Deep graph representations embed network information for robust disease marker identification

We report that the accurate disease diagnosis and prognosis based on omics data rely on the effective identification of robust prognostic and diagnostic markers that reflect the states of the biological processes underlying the disease pathogenesis and progression. In this article, we present GCNCC, a Graph Convolutional Network-based approach for Clustering and Classification, that can identify highly effective and robust network-based disease markers. Based on a geometric deep learning framework, GCNCC learns deep network representations by integrating gene expression data with protein interaction data to identify highly reproducible markers with consistently accurate prediction performance across independent datasets possibly from different platforms. GCNCC identifies these markers by clustering the nodes in the protein interaction network based on latent similarity measures learned by the deep architecture of a graph convolutional network, followed by a supervised feature selection procedure that extracts clusters that are highly predictive of the disease state. By benchmarking GCNCC based on independent datasets from different diseases (psychiatric disorder and cancer) and different platforms (microarray and RNA-seq), we show that GCNCC outperforms other state-of-the-art methods in terms of accuracy and reproducibility.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Rolling Root Mean Square Based Multimodal Anomaly Detection for Real Time Monitoring of Smart Grid

Reliable real-time monitoring is valuable for maintaining the operational integrity of modern electrical smart grids. Deployment of heterogeneous sensing technologies in substations has enabled high-resolution, multichannel waveform monitoring, but also introduces challenges for anomaly detection due to noise, baseline drift, and modality-dependent signal characteristics. In this work, we present a computationally efficient unsupervised method for multimodal event detection based on Rolling Root Mean Square based Event Detection (RRMSED). The method is developed using in-house, field deployed sensors collecting data at a utility substation. The sensing system comprises voltage and current sensors, triaxial accelerometers, and magnetometers, collectively capturing electrical, vibrational, and magnetic waveform measurements at high temporal resolution. RRMSED operates by extracting rolling RMS energy features and their first-order temporal differences from consecutive waveform segments for each channel and then applying channel-specific statistical thresholds learned from historical data. A persistence-based exceedance logic is employed to robustly identify transient events while suppressing impulsive noise, and to provide precise temporal localization with high resolution. The framework is designed for continuous server-side operation and can be deployed in real time without requiring complex models. Experiments on simulated waveform data with known ground truth demonstrate low false positive (FP) and false negative (FN) rates. Application to real substation data shows RRMSED to identify events that are not captured by conventional monitoring indicators including fast transient detection algorithm currently deployed in the system. These results indicate that rolling RMS based features provide an effective and practical basis for real-time multimodal event detection in smart-grid substations.

Mukherjee, Subrata [ORNL] (ORCID:0000000309930338)↗
DOE OSTI2024

INSURE: An Information Theory iNspired diSentanglement and pURification modEl for Domain Generalization

Domain Generalization (DG) aims to learn a generalizable model on the unseen target domain by only training on the multiple observed source domains. Although a variety of DG methods have focused on extracting domain-invariant features, the domain-specific class-relevant features have attracted attention and been argued to benefit generalization to the unseen target domain. To take into account the class-relevant domain-specific information, in this paper we propose an Information theory iNspired diSentanglement and pURification modEl (INSURE) to explicitly disentangle the latent features to obtain sufficient and compact (necessary) class-relevant feature for generalization to the unseen domain. Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information. Additionally, we further propose a paired purification loss function to let the auxiliary feature discard all the class-relevant information and thus the class-relevant feature will contain sufficient and compact (necessary) class-relevant information. Moreover, instead of using multiple encoders, we propose to use a learnable binary mask as our disentangler to make the disentanglement more efficient and make the disentangled features complementary to each other. We conduct extensive experiments on five widely used DG benchmark datasets including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. The proposed INSURE achieves state-of-the-art performance. We also empirically show that domain-specific class-relevant features are beneficial for domain generalization. The code is available at https://github.com/yuxi120407/INSURE .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Learning-Based Real-Time Event Identification Using Rich Real PMU Data

A large-scale deployment of phasor measurement units (PMUs) that reveal the inherent physical laws of power systems from a data perspective enables an enhanced awareness of power system operation. However, the high-granularity and non-stationary nature of PMU data and imperfect data quality could bring great technical challenges for real-time system event identification. To address these challenges, this paper proposes a two-stage learning-based framework. In the first stage, a Markov transition field (MTF) algorithm is exploited to extract the latent data features by encoding temporal dependency and transition statistics of PMU data in graphs. Then, a spatial pyramid pooling (SPP)-aided convolutional neural network (CNN) is established to efficiently and accurately identify power events. The proposed method fully builds on and is also tested on a large real-world dataset from several tens of PMU sources (and the corresponding event logs), located across the U.S., with a time span of two consecutive years. We report the numerical results validate that our method has high identification accuracy while showing good robustness against poor data quality.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2015

SU-E-T-01: (In)dependence of Plan Quality On Treatment Modalities and Target-To-Critical Structure Geometry for Brain Tumor

Purpose: To evaluate and test the hypothesis that plan quality may be systematically affected by treatment delivery techniques and target-tocritical structure geometric relationship in radiotherapy for brain tumor. Methods: Thirty-four consecutive brain tumor patients treated between 2011–2014 were analyzed. Among this cohort, 10 were planned with 3DCRT, 11 with RadipArc, and 13 with helical IMRT on TomoTherapy. The selected dosimetric endpoints (i.e., PTV V100, maximum brainstem/chiasm/ optic nerve doses) were considered as a vector in a highdimensional space. A Pareto analysis was performed to identify the subset of Pareto-efficient plans.The geometric relationships, specifically the overlapping volume and centroid-of-mass distance between each critical structure to the PTV were extracted as potential geometric features. The classification-tree analyses were repeated using these geometric features with and without the treatment modality as an additional categorical predictor. In both scenarios, the dominant features to prognosticate the Pareto membership were identified and the tree structures to provide optimal inference were recorded. The classification performance was further analyzed to determine the role of treatment modality in affecting plan quality. Results: Seven Pareto-efficient plans were identified based on dosimetric endpoints (3 from 3DCRT, 3 from RapicArc, 1 from Tomo), which implies that the evaluated treatment modality may have a minor influence on plan quality. Classification trees with/without the treatment modality as a predictor both achieved accuracy of 88.2%: with 100% sensitivity and 87.1% specificity for the former, and 66.7% sensitivity and 96.0% specificity for the latter. The coincidence of accuracy from both analyses further indicates no-to-weak dependence of plan quality on treatment modality. Both analyses have identified the brainstem to PTV distance as the primary predictive feature for Pareto-efficiency. Conclusion: Pareto evaluation and classification-tree analyses have indicated that plan quality depends strongly on geometry for brain tumor, specifically PTV-tobrain-stem-distance but minimally on treatment modality.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

TU-CD-BRB-08: Radiomic Analysis of FDG-PET Identifies Novel Prognostic Imaging Biomarkers in Locally Advanced Pancreatic Cancer Patients Treated with SBRT

Purpose: This study aims to identify novel prognostic imaging biomarkers in locally advanced pancreatic cancer (LAPC) using quantitative, high-throughput image analysis. Methods: 86 patients with LAPC receiving chemotherapy followed by SBRT were retrospectively studied. All patients had a baseline FDG-PET scan prior to SBRT. For each patient, we extracted 435 PET imaging features of five types: statistical, morphological, textural, histogram, and wavelet. These features went through redundancy checks, robustness analysis, as well as a prescreening process based on their concordance indices with respect to the relevant outcomes. We then performed principle component analysis on the remaining features (number ranged from 10 to 16), and fitted a Cox proportional hazard regression model using the first 3 principle components. Kaplan-Meier analysis was used to assess the ability to distinguish high versus low-risk patients separated by median predicted survival. To avoid overfitting, all evaluations were based on leave-one-out cross validation (LOOCV), in which each holdout patient was assigned to a risk group according to the model obtained from a separate training set. Results: For predicting overall survival (OS), the most dominant imaging features were wavelet coefficients. There was a statistically significant difference in OS between patients with predicted high and low-risk based on LOOCV (hazard ratio: 2.26, p<0.001). Similar imaging features were also strongly associated with local progression-free survival (LPFS) (hazard ratio: 1.53, p=0.026) on LOOCV. In comparison, neither SUVmax nor TLG was associated with LPFS (p=0.103, p=0.433) (Table 1). Results for progression-free survival and distant progression-free survival showed similar trends. Conclusion: Radiomic analysis identified novel imaging features that showed improved prognostic value over conventional methods. These features characterize the degree of intra-tumor heterogeneity reflected on FDG-PET images, and their biological underpinnings warrant further investigation. If validated in large, prospective cohorts, this method could be used to stratify patients based on individualized risk.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

Automated segmentation of dental CBCT image with prior-guided sequential random forests

Purpose: Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate 3D models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the image artifacts caused by beam hardening, imaging noise, inhomogeneity, truncation, and maximal intercuspation, it is difficult to segment the CBCT. Methods: In this paper, the authors present a new automatic segmentation method to address these problems. Specifically, the authors first employ a majority voting method to estimate the initial segmentation probability maps of both mandible and maxilla based on multiple aligned expert-segmented CBCT images. These probability maps provide an important prior guidance for CBCT segmentation. The authors then extract both the appearance features from CBCTs and the context features from the initial probability maps to train the first-layer of random forest classifier that can select discriminative features for segmentation. Based on the first-layer of trained classifier, the probability maps are updated, which will be employed to further train the next layer of random forest classifier. By iteratively training the subsequent random forest classifier using both the original CBCT features and the updated segmentation probability maps, a sequence of classifiers can be derived for accurate segmentation of CBCT images. Results: Segmentation results on CBCTs of 30 subjects were both quantitatively and qualitatively validated based on manually labeled ground truth. The average Dice ratios of mandible and maxilla by the authors’ method were 0.94 and 0.91, respectively, which are significantly better than the state-of-the-art method based on sparse representation (p-value < 0.001). Conclusions: The authors have developed and validated a novel fully automated method for CBCT segmentation.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2024

pnnl/SAMIAm

We apply semantic boosting to the Segment Anything Model (SAM) to obtain microstructure segmentation for transmission electron microscopy. Our booster, SAM-I-Am, extracts geometric and textural features of various intermediate masks to perform mask removal and mask merging operations

Mesfin, Waqwoya↗
DOE OSTI2023

Integrating LEO and GEO Observations: Toward Optimal Summertime Satellite Precipitation Retrieval

Abstract Reliable quantitative precipitation estimation with a rich spatiotemporal resolution is vital for understanding the Earth’s hydrological cycle. Precipitation estimation over land and coastal regions is necessary for addressing the high degree of spatial heterogeneity of water availability and demand, and for resolving the extremes that modulate and amplify hazards such as flooding and landslides. Advancements in computation power along with unique high spatiotemporal and spectral resolution data streams from passive meteorological sensors aboard geosynchronous Earth-orbiting (GEO) and low Earth-orbiting (LEO) satellites offer exciting opportunities to retrieve information about surface precipitation phenomena using data-driven machine learning techniques. In this study, the capabilities of U-Net–like architecture are investigated to map instantaneous, summertime surface precipitation intensity at the spatial resolution of 2 km. The calibrated brightness temperature products from the Global Precipitation Measurement (GPM) Microwave Imager (GMI) radiometer are combined with multispectral images (visible, near-infrared, and infrared bands) from the Advanced Baseline Imager (ABI) aboard the GOES-R satellites as main inputs to the U-Net–like precipitation algorithm. Total precipitable water and 2-m temperature from the Global Forecast System (GFS) model are also used as auxiliary inputs to the model. The results show that the U-Net–like algorithm can capture fine-scale patterns and intensity of surface precipitation at high spatial resolution over stratiform and convective precipitation regimes. The evaluations reveal the potential of extracting relevant, high spatial features over complex surface types such as mountainous regions and coastlines. The algorithm allows users to interpret the inputs’ importance and can serve as a starting point for further exploration of precipitation systems within the field of hydrometeorology.

Meteorology & Atmospheric Sciences↗
DOE OSTI2024

Deep learning enhanced super-resolution x-ray fluorescence microscopy by a dual-branch network

X-ray fluorescence (XRF) microscopy is a powerful technique for quantifying the distribution of elements in complex materials, which makes it a crucial imaging technique across a wide range of disciplines in physical and biological sciences, including chemistry, materials science, microbiology, and geosciences. However, as a scanning microscopy technique, the spatial resolution of XRF imaging is inherently constrained by the x-ray probe profile and scanning step size. Here we propose a dual-branch machine learning (ML) model, which can extract scale-variant features and bypass abundant low-frequency information separately, to enhance the spatial resolution of the XRF images by mitigating the effects of blurring from the probe profile. The model is trained by simulated natural images, and a two-stage training strategy is used to overcome the domain gap between the natural images and experimental data. The tomography reconstruction from enhanced XRF projections shows an improvement in resolution by a scale factor of four and reveals distinct internal features invisible in low-resolution XRF within a battery sample. This study offers a promising approach for obtaining high-resolution XRF imaging from its low-resolution version, paving the way for future investigations in a broader range of disciplines and materials.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Limited-view Cone Beam CT reconstruction using 3D Patch-based Supervised and Adversarial Learning [Slides]

We present a novel machine learning CNN architecture that can learn from limited data combined appropriately with physics and statistical priors (e.g., forward models and noise models). To address the limited availability of training data we adopt a 3D patch-based approach for our models. Patch-based learning is central to several image reconstruction methods and demands fewer training data than DL approaches, as a single data volume can be broken into several millions of overlapping 3D sub-volumes or patches. This creates a very large number of training sub-volumes from a limited number of overall image volumes. A 3D Generative Adversarial Networks (GAN) is then trained to remove artifacts at the sub-volume level. The combination of a sub-volume-based approach with DL allows us to exploit the richness of the latter in extracting and representing image features, while avoiding risks associated with overfitting due to limited training data.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

3P Program: Phenotyping X Prediction = Productivity (Final Scientific/Technical Report)

The goal of the 3P Program was to establish integrated, real-time phenotyping and to analyze above- and below-ground plant architecture and total carbon partitioning and allocation to predict heterosis and develop superior crop hybrids by fully leveraging the Sorghum gene pool. There were two overarching themes: 1) the development of a new crop improvement approach utilizing advances in high-throughput phenotyping (HTP), computing, and genomics for public dissemination and 2) leveraging this platform for sorghum crop improvement and commercialization. The Clemson team worked on creating genomic resources and using both statistical learning and high-throughput phenotyping in genomics-assisted breeding. Research was broadly interested in the genetics of carbon partitioning, with the aim of improving crop performance and achieving sustainability. The technology and resources created can be readily found in the public domain and serve to advance scientific understanding of crop genomics and breeding. Genomic prediction was able to identify top crosses to be made, and a hybrid prediction pipeline is in place to drive year-over-year genetic gain. Roots have long been ignored by plant breeders and agronomists, not because they are unimportant but because they are hard to measure. This is an untapped white space of potential insight and innovation. To address this, Hi Fidelity Genetics developed the RootTracker to measure roots in the field on a continuous basis. A database system called RootTracker Tracker was developed to handle data coming from the RootTrackers. In using this device, valuable data was observed for plant breeding, hydrochemical development, and other agricultural biology applications. Carnegie Mellon’s goal was developing new techniques to generate high-resolution 3D models of plants from data collected in the field. The idea was that more useful and more informative phenotypes could be extracted by resolving small features, such as seeds and flowers, and that by modeling in 3D, the spatial structure of plants could be examined. To achieve this, multiple images collected by a new small format structured light stereo imager were fused together. A sorghum panicle modeling pipeline was developed to allow the collection and processing of data. Carolina Seed Systems is an agricultural technology company focused on decarbonizing the agricultural system. Their technology pipeline serves to drive fundamental progress towards creation and distribution of carbon negative crops. The genomic and the engineering technology developed through the 3P Program was leveraged to deliver both value and sustainability from the grower to the consumer. Promising sorghum hybrids were scaled up and commercialized. The overall goal of our research was to integrate, create, and deploy genetic and engineering concepts and technologies to enhance crop productivity in a sustainable fashion. The combination of public and private partners allowed the basic research and hypothesis testing to be quickly accelerated for commercial application by the companies yet maintained that the core framework and academic insights remain in the public domain for continued market disruption, competition, and innovation.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A novel transfer learning framework for sorghum biomass prediction using UAV-based remote sensing data and genetic markers

Yield for biofuel crops is measured in terms of biomass, so measurements throughout the growing season are crucial in breeding programs, yet traditionally time- and labor-consuming since they involve destructive sampling. Modern remote sensing platforms, such as unmanned aerial vehicles (UAVs), can carry multiple sensors and collect numerous phenotypic traits with efficient, non-invasive field surveys. However, modeling the complex relationships between the observed phenotypic traits and biomass remains a challenging task, as the ground reference data are very limited for each genotype in the breeding experiment. In this study, a Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) model is proposed for sorghum biomass prediction. The architecture is designed to exploit the time series remote sensing and weather data, as well as static genotypic information. As a large number of features have been derived from the remote sensing data, feature importance analysis is conducted to identify and remove redundant features. A strategy to extract representative information from high-dimensional genetic markers is proposed. To enhance generalization and minimize the need for ground reference data, transfer learning strategies are proposed for selecting the most informative training samples from the target domain. Consequently, a pre-trained model can be refined with limited training samples. Field experiments were conducted over a sorghum breeding trial planted in multiple years with more than 600 testcross hybrids. The results show that the proposed LSTM-based RNN model can achieve high accuracies for single year prediction. Further, with the proposed transfer learning strategies, a pre-trained model can be refined with limited training samples from the target domain and predict biomass with an accuracy comparable to that from a trained-from-scratch model for both multiple experiments within a given year and across multiple years.

36 MATERIALS SCIENCE↗
DOE OSTI2016

COLD MILKY WAY H i GAS IN FILAMENTS

We investigate data from the Galactic Effelsberg-Bonn H i Survey, supplemented with data from the third release of the Galactic All Sky Survey (GASS III) observed at Parkes. We explore the all-sky distribution of the local Galactic H i gas with |v{sub LSR}|<25 km s{sup −1} on angular scales of 11′–16′. Unsharp masking is applied to extract small-scale features. We find cold filaments that are aligned with polarized dust emission and conclude that the cold neutral medium (CNM) is mostly organized in sheets that are, because of projection effects, observed as filaments. These filaments are associated with dust ridges, aligned with the magnetic field measured on the structures by Planck at 353 GHz. The CNM above latitudes |b|>20{sup ∘} is described by a log-normal distribution, with a median Doppler temperature T{sub D} = 223 K, derived from observed line widths that include turbulent contributions. The median neutral hydrogen (H i) column density is N{sub H i} ≃ 10{sup 19.1} cm{sup −2}. These CNM structures are embedded within a warm neutral medium with N{sub H i} ≃ 10{sup 20} cm{sup −2}. Assuming an average distance of 100 pc, we derive for the CNM sheets a thickness of ≲0.3 pc. Adopting a magnetic field strength of B{sub tot} = (6.0 ± 1.8) μG, proposed by Heiles and Troland, and assuming that the CNM filaments are confined by magnetic pressure, we estimate a thickness of 0.09 pc. Correspondingly, the median volume density is in the range 14 ≲ n ≲ 47 cm{sup −3}.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2016

Utilizing Genetic Programming to Identify Failures in ICS Networks

Previously, researchers have attempted to apply machine learning techniques to network anomaly detection problems. Due to the staggering amount of variety that can occur in normal networks, the results have often been underwhelming. These challenges are far less pronounced when considering industrial control system (ICS) networks. The recurrent nature of these networks results in less noise and more consistent patterns for a machine learning algorithm to recognize. Here, we propose a method of evolving decision trees through genetic programming (GP) in order to detect network anomalies, such as device outages. Our approach extracts over a dozen features from network packet captures and netflows, normalizes them, and relates them in decision trees using fuzzy logic operators. Furthermore, the trees were used to detect three specific network events from three different points on the network across a statistically significant number of runs and achieved 100% accuracy on five of the nine experiments. When the trees attempted to detect more challenging events at points of presence further from the occurrence, the accuracy averaged to above 98%. Finally, using our method, all of the evolutionary cycles of the GP algorithm are computed a-priori, allowing the best resultant trees to be deployed as semi-real-time sensors with little overhead.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Robotic Understanding of Spatial Relationships Using Neural-Logic Learning

Understanding spatial relations of objects is critical in many robotic applications such as grasping, manipulation, and obstacle avoidance. Humans can simply reason object's spatial relations from a glimpse of a scene based on prior knowledge of spatial constraints. The proposed method enables a robot to comprehend spatial relationships among objects from RGB-D data. This paper proposed a neural-logic learning framework to learn and reason spatial relations from raw data by following logic rules on spatial constraints. The neural-logic network consists of three blocks: grounding block, spatial logic block, and inference block. The grounding block extracts high-level features from the raw sensory data. The spatial logic blocks can predicate fundamental spatial relations by training a neural network with spatial constraints. The inference block can infer complex spatial relations based on the predicated fundamental spatial relations. Simulations and robotic experiments evaluated the performance of the proposed method.

Wang, Dali↗
DOE OSTI2022

Predicting failure parameters of semiconductor devices subjected to stress conditions

A method for predicting failure parameters of semiconductor devices can include receiving a set of data that includes (i) characteristics of a sample semiconductor device, and (ii) parameters characterizing a stress condition. The method further includes extracting a plurality of feature values from the set of data and inputting the plurality of feature values into a trained model executing on the one or more processors, wherein the trained model is configured according to an artificial intelligence (AI) algorithm based on a previous plurality of feature values, and wherein the trained model is operable to output a failure prediction based on the plurality of feature values. Further, the method includes generating, via the trained model, a predicted failure parameter of the sample semiconductor device due to the stress condition.

Ahmed, Moinuddin↗
DOE OSTI2020

On Temperature Limits for the Outer Surface of a Container in a Disposal Facility - 20313

The temperature in a disposal facility for high-level radioactive waste (HLRW) is an issue for safety. When the recommencement of the search for and selection of a site for a disposal facility for HLRW in Germany was stipulated by the Site Selection Act (StandAG 2017) in 2017, a precautionary temperature limit of 100 deg. C on the outer surface of the containers with high-level radioactive waste in the disposal facility section was set. This precautionary temperature limit shall be applied in preliminary safety analyses provided that the 'maximum physically possible temperatures' in the respective host rocks have not yet been determined due to pending research. Therefore, this issue is addressed and discussed in this paper, contributing to 'pending research' by a review of the literature. This paper briefly discusses a few examples of thermohydraulic, mechanical, chemical and biological processes in a disposal facility, because temperature limits are derived based on safety impacts regarding THMCB-processes. The temperature-dependent processes have been extracted from databases for features, events and processes (FEP-databases). Furthermore, it is discussed if the feasibility to retrieve and recover HLRW is hampered at high temperatures. A design temperature concerning single components of a disposal facility for the preservation of their features can be derived when a safety concept is established. However, the interactions of all relevant processes in a disposal concept must be considered to determine a specific temperature limit for the outer surface of the containers. Therefore, applicable temperature limits may vary for particular safety and disposal concepts in the following host rocks: rock salt, clay stone and crystalline rock. Technical solutions for retrieval and design options for recovery seem to be viable up to temperatures of 200 deg. C with different, sometimes severe, downsides according to expert judgement. Temperature limits regarding the outer surface of the containers can be derived specifically for each safety concept and design of the disposal facility in a host rock. General temperature limits without reference to specific safety concepts or the particular design of the disposal facility may narrow down the possibilities for optimisation of the disposal facility and could adversely affect the site selection process in finding the best suitable site. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗