Biology subjects

Chades, I.

Publications and source records attributed to Chades, I..

2 recordsLinked to original sources

bioRxiv2024

Developing new technologies to protect ecosystems: planning with adaptive management

Technology development is an essential investment for policymakers to address contemporary global crises, including climate change, biodiversity loss, the energy transition, and emergent infectious diseases. However, investing limited resources in the development of new technologies is risky. The research and development process is unpredictable, with unknown timelines and outcomes. In addition, even after successful development, the effects of deploying a new technology remain uncertain. When confronted with these uncertainties, policymakers must determine how long they should allocate resources to developing new technologies. Informed decisions require anticipating possible successes and failures of both technology development and deployment, which is a challenging optimisation task when managing dynamic systems, such as threatened ecological systems. Using an adaptive management approach from Artificial Intelligence, we discover a time limit new technologies should be developed for, which balances costs, benefits, and uncertainties during development and deployment. We extract clear and transparent general rules for investing in new technologies, building on an analytical approximation. Using Australias Great Barrier Reef as a case study, we demonstrate how characteristics of the managed system influence the optimal investment strategy. Our approach can inform the development of new technologies in multiple domains including biodiversity conservation, public health, energy production, and the technology industry more broadly. SignificanceTechnology development is essential to address the crises our world faces, such as ecosystem collapse. With limited resources, policymakers must decide whether to invest in developing new technologies and, if ever, when to stop. Informed decisions require anticipating possible failures of both technology development and deployment, a challenging task when dealing with changing systems. Using an Artificial Intelligence approach, we find a time limit for technology development that depends on characteristics of the managed ecosystem. This work can guide technology investments in many domains such as biodiversity conservation, epidemiology, energy production and the technology industry more broadly.

ecology↗

bioRxiv2024

Interpretable Solutions for Stochastic Dynamic Programming

O_LIIn conservation of biodiversity, natural resource management and behavioural ecology, stochastic dynamic programming, and its mathematical framework, Markov decision processes (MDPs), are used to inform sequential decision-making under uncertainty. Models and solutions of Markov decision problems should be interpretable to derive useful guidance for managers and applied ecologists. However, MDP solutions that have thousands of states are often difficult to understand. Difficult to interpret solutions are unlikely to be applied, and thus we are missing an opportunity to improve decision-making. One way of increasing interpretability is to decrease the number of states. C_LIO_LIBuilding on recent artificial intelligence advances, we introduce a novel approach to compute more compact representations of MDP models and solutions as an attempt at improving interpretability. This approach reduces the size of the number of states to a maximum number K while minimising the loss of performance compared to the original larger number of states. The reduced MDP is called a K-MDP. We present an algorithm to compute K-MDPs and assess its performance on three case studies of increasing complexity from the literature. We provide the code as a MATLAB package along with a set of illustrative problems. C_LIO_LIWe found that K-MDPs can achieve a substantial reduction of the number of states with a small loss of performance for all case studies. For example, for a conservation problem involving Northern Abalone and Sea Otters, we reduce the number of states from 819 to 5 states while incurring a loss of performance of only 1%. For a dynamic reserve selection problem with seven dimensions, while an impressive reduction in the number of states was achieved, interpreting the optimal solutions remained challenging. C_LIO_LIModelling problems as Markov decision processes requires experience. While several models may represent the same problem, reducing the number of states is likely to make solutions and models more interpretable and facilitate the extraction of meaningful recommendations. We hope that this approach will contribute to the uptake of stochastic dynamic programming applications and stimulate further research to increase interpretability of stochastic dynamic programming solutions. C_LI

ecology↗