TY  - JOUR
A1  - Zurell, Damaris
A1  - König, Christian
A1  - Malchow, Anne-Kathleen
A1  - Kapitza, Simon
A1  - Bocedi, Greta
A1  - Travis, Justin M. J.
A1  - Fandos, Guillermo
T1  - Spatially explicit models for decision-making in animal conservation and restoration
JF  - Ecography : pattern and diversity in ecology / Nordic Ecologic Society Oikos
N2  - Models are useful tools for understanding and predicting ecological patterns and processes. Under ongoing climate and biodiversity change, they can greatly facilitate decision-making in conservation and restoration and help designing adequate management strategies for an uncertain future. Here, we review the use of spatially explicit models for decision support and to identify key gaps in current modelling in conservation and restoration. Of 650 reviewed publications, 217 publications had a clear management application and were included in our quantitative analyses. Overall, modelling studies were biased towards static models (79%), towards the species and population level (80%) and towards conservation (rather than restoration) applications (71%). Correlative niche models were the most widely used model type. Dynamic models as well as the gene-to-individual level and the community-to-ecosystem level were underrepresented, and explicit cost optimisation approaches were only used in 10% of the studies. We present a new model typology for selecting models for animal conservation and restoration, characterising model types according to organisational levels, biological processes of interest and desired management applications. This typology will help to more closely link models to management goals. Additionally, future efforts need to overcome important challenges related to data integration, model integration and decision-making. We conclude with five key recommendations, suggesting that wider usage of spatially explicit models for decision support can be achieved by 1) developing a toolbox with multiple, easier-to-use methods, 2) improving calibration and validation of dynamic modelling approaches and 3) developing best-practise guidelines for applying these models. Further, more robust decision-making can be achieved by 4) combining multiple modelling approaches to assess uncertainty, and 5) placing models at the core of adaptive management. These efforts must be accompanied by long-term funding for modelling and monitoring, and improved communication between research and practise to ensure optimal conservation and restoration outcomes.
KW  - adaptive management
KW  - biodiversity conservation
KW  - cost optimisation
KW  - ecosystem restoration
KW  - global change
KW  - predictive models
Y1  - 2021
U6  - https://doi.org/10.1111/ecog.05787
SN  - 1600-0587
IS  - 4
SP  - 1
EP  - 16
PB  - Wiley-Blackwell
CY  - Oxford
ER  - 
TY  - JOUR
A1  - Chen, Junchao
A1  - Lange, Thomas
A1  - Andjelkovic, Marko
A1  - Simevski, Aleksandar
A1  - Lu, Li
A1  - Krstic, Milos
T1  - Solar particle event and single event upset prediction from SRAM-based monitor and supervised machine learning
JF  - IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers
N2  - The intensity of cosmic radiation may differ over five orders of magnitude within a few hours or days during the Solar Particle Events (SPEs), thus increasing for several orders of magnitude the probability of Single Event Upsets (SEUs) in space-borne electronic systems. Therefore, it is vital to enable the early detection of the SEU rate changes in order to ensure timely activation of dynamic radiation hardening measures. In this paper, an embedded approach for the prediction of SPEs and SRAM SEU rate is presented. The proposed solution combines the real-time SRAM-based SEU monitor, the offline-trained machine learning model and online learning algorithm for the prediction. With respect to the state-of-the-art, our solution brings the following benefits: (1) Use of existing on-chip data storage SRAM as a particle detector, thus minimizing the hardware and power overhead, (2) Prediction of SRAM SEU rate one hour in advance, with the fine-grained hourly tracking of SEU variations during SPEs as well as under normal conditions, (3) Online optimization of the prediction model for enhancing the prediction accuracy during run-time, (4) Negligible cost of hardware accelerator design for the implementation of selected machine learning model and online learning algorithm. The proposed design is intended for a highly dependable and self-adaptive multiprocessing system employed in space applications, allowing to trigger the radiation mitigation mechanisms before the onset of high radiation levels.
KW  - Machine learning
KW  - Single event upsets
KW  - Random access memory
KW  - monitoring
KW  - machine learning algorithms
KW  - predictive models
KW  - space missions
KW  - solar particle event
KW  - single event upset
KW  - machine learning
KW  - online learning
KW  - hardware accelerator
KW  - reliability
KW  - self-adaptive multiprocessing system
Y1  - 2022
U6  - https://doi.org/10.1109/TETC.2022.3147376
SN  - 2168-6750
VL  - 10
IS  - 2
SP  - 564
EP  - 580
PB  - Institute of Electrical and Electronics Engineers
CY  - [New York, NY]
ER  -