Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAutonomous decision-making against induced seismicity in deep fluid injections
165
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
The rise in the frequency of anthropogenic earthquakes due to deep fluid injections is posing serious economic, societal, and legal challenges to geo-energy and waste-disposal projects. We propose an actuarial approach to mitigate this risk, first by defining an autonomous decision-making process based on an adaptive traffic light system (ATLS) to stop risky injections, and second by quantifying a cost of public safety based on the probability of an injection-well being abandoned. The ATLS underlying statistical model is first confirmed to be representative of injection-induced seismicity, with examples taken from past reservoir stimulation experiments (mostly from Enhanced Geothermal Systems, EGS). Then the decision strategy is formalized: Being integrable, the model yields a closed-form ATLS solution that maps a risk-based safety standard or norm to an earthquake magnitude not to exceed during stimulation. Finally, the EGS levelized cost of electricity (LCOE) is reformulated in terms of null expectation, with the cost of abandoned injection-well implemented. We find that the price increase to mitigate the increased seismic risk in populated areas can counterbalance the heat credit. However this public safety cost disappears if buildings are based on earthquake-resistant designs or if a more relaxed risk safety standard or norm is chosen.
rate research
Read More
We report a similarity of fluctuations in equilibrium critical phenomena and non-equilibrium systems, which is based on the concept of natural time. The world-wide seismicity as well as that of San Andreas fault system and Japan are analyzed. An order parameter is chosen and its fluctuations relative to the standard deviation of the distribution are studied. We find that the scaled distributions fall on the same curve, which interestingly exhibits, over four orders of magnitude, features similar to those in several equilibrium critical phenomena (e.g., 2D Ising model) as well as in non-equilibrium systems (e.g., 3D turbulent flow).
We present the condensation method that exploits the heterogeneity of the probability distribution functions (PDF) of event locations to improve the spatial information content of seismic catalogs. The method reduces the size of seismic catalogs while improving the access to the spatial information content of seismic catalogs. The PDFs of events are first ranked by decreasing location errors and then successively condensed onto better located and lower variance event PDFs. The obtained condensed catalog attributes different weights to each event, providing an optimal spatial representation with respect to the spatially varying location capability of the seismic network. Synthetic tests on fractal distributions perturbed with realistic location errors show that condensation improves spatial information content of the original catalog. Applied to Southern California seismicity, the new condensed catalog highlights major mapped fault traces and reveals possible additional structures while reducing the catalog length by ~25%. The condensation method allows us to account for location error information within a point based spatial analysis. We demonstrate this by comparing the multifractal properties of the condensed catalog locations with those of the original catalog. We evidence different spatial scaling regimes characterized by distinct multifractal spectra and separated by transition scales. We interpret the upper scale as to agree with the thickness of the brittle crust, while the lower scale (2.5km) might depend on the relocation procedure. Accounting for these new results, the Epidemic Type Aftershock Model formulation suggests that, contrary to previous studies, large earthquakes dominate the earthquake triggering process. This implies that the limited capability of detecting small magnitude events cannot be used to argue that earthquakes are unpredictable in general.
The standard paradigm to describe seismicity induced by fluid injection is to apply nonlinear diffusion dynamics in a poroelastic medium. I show that the spatiotemporal behaviour and rate evolution of induced seismicity can, instead, be expressed by geometric operations on a static stress field produced by volume change at depth. I obtain laws similar in form to the ones derived from poroelasticity while requiring a lower description length. Although fluid flow is known to occur in the ground, it is not pertinent to the behaviour of induced seismicity. The proposed model is equivalent to the static stress model for tectonic foreshocks generated by the Non- Critical Precursory Accelerating Seismicity Theory. This study hence verifies the explanatory power of this theory outside of its original scope.
Knowledge transfer is a promising concept to achieve real-time decision-making for autonomous vehicles. This paper constructs a transfer deep reinforcement learning framework to transform the driving tasks in inter-section environments. The driving missions at the un-signalized intersection are cast into a left turn, right turn, and running straight for automated vehicles. The goal of the autonomous ego vehicle (AEV) is to drive through the intersection situation efficiently and safely. This objective promotes the studied vehicle to increase its speed and avoid crashing other vehicles. The decision-making pol-icy learned from one driving task is transferred and evaluated in another driving mission. Simulation results reveal that the decision-making strategies related to similar tasks are transferable. It indicates that the presented control framework could reduce the time consumption and realize online implementation.
We study the design of learning architectures for behavioural planning in a dense traffic setting. Such architectures should deal with a varying number of nearby vehicles, be invariant to the ordering chosen to describe them, while staying accurate and compact. We observe that the two most popular representations in the literature do not fit these criteria, and perform badly on an complex negotiation task. We propose an attention-based architecture that satisfies all these properties and explicitly accounts for the existing interactions between the traffic participants. We show that this architecture leads to significant performance gains, and is able to capture interactions patterns that can be visualised and qualitatively interpreted. Videos and code are available at https://eleurent.github.io/social-attention/.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
