An official website of the United States government
Research exploring how to support decision-making has often used machine learning to automate or assist human decisions. We take an alternative approach for improving decision-making, using machine learning to help stakeholders surface ways to improve and make fairer decision-making processes. We created "Deliberating with AI", a web tool that enables people to create and evaluate ML models in order to examine strengths and shortcomings of past decision-making and deliberate on how to improve future decisions. We apply this tool to a context of people selection, having stakeholders---decision makers (faculty) and decision subjects (students)---use the tool to improve graduate school admission decisions. Through our case study, we demonstrate how the stakeholders used the web tool to create ML models that they used as boundary objects to deliberate over organization decision-making practices. We share insights from our study to inform future research on stakeholder-centered participatory AI design and technology for organizational decision-making.
more »
« less
Trustworthy Predictive Algorithms for Complex Forest System Decision-Making
Advances in predictive algorithms are revolutionizing how we understand and design effective decision support systems in many sectors. The expanding role of predictive algorithms is part of a broader movement toward using data-driven machine learning (ML) for modalities including images, natural language, speech. This article reviews whether and to what extent predictive algorithms can assist decision-making in forest conservation and management. Although state-of-the-art ML algorithms provide new opportunities, adoption has been slow in forest decision-making. This review shows how domain-specific characteristics, such as system complexity, impose limits on using predictive algorithms in forest conservation and management. We conclude with possible directions for developing new predictive tools and approaches to support meaningful forest decisions through easily interpretable and explainable recommendations.
more »
« less
- Award ID(s):
- 1717530
- PAR ID:
- 10276335
- Date Published:
- Journal Name:
- Frontiers in Forests and Global Change
- Volume:
- 3
- ISSN:
- 2624-893X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Intertemporal choices involve assessing options with different reward amounts available at different time delays. The similarity approach to intertemporal choice focuses on judging how similar amounts and delays are. Yet we do not fully understand the cognitive process of how these judgments are made. Here, we use machine-learning algorithms to predict similarity judgments to (1) investigate which algorithms best predict these judgments, (2) assess which predictors are most useful in predicting participants’ judgments, and (3) determine the minimum number of judgments required to accurately predict future judgments. We applied eight algorithms to similarity judgments for reward amount and time delay made by participants in two data sets. We found that neural network, random forest, and support vector machine algorithms generated the highest out-of-sample accuracy. Though neural networks and support vector machines offer little clarity in terms of a possible process for making similarity judgments, random forest algorithms generate decision trees that can mimic the cognitive computations of human judgment making. We also found that the numerical difference between amount values or delay values was the most important predictor of these judgments, replicating previous work. Finally, the best performing algorithms such as random forest can make highly accurate predictions of judgments with relatively small sample sizes (~ 15), which will help minimize the numbers of judgments required to extrapolate to new value pairs. In summary, machine-learning algorithms provide both theoretical improvements to our understanding of the cognitive computations involved in similarity judgments and intertemporal choices as well as practical improvements in designing better ways of collecting data.more » « less
-
Rural out-migration was a rare socio-economic phenomenon when community forestry began in the 1980s in Nepal. Now, out-migration significantly influences nearly every aspect of rural livelihoods in the country. However, it is unclear how out-migration affects community forestry governance, which is essential for sustainable rural development. Therefore, this paper addresses the following research question: Does rural out-migration affect forest users’ participation in community forestry decision-making and management practices? This paper draws on data collected from an extensive survey of 415 households from 15 community forest user groups in 2 Mid-Hill districts of Nepal. The research used ordered-logit regression to model the impacts of out-migration on participation in forest management and decision-making, while controlling for a number of other socio-economic factors. The model results show that total household size and number of internal migrants, together with multiple resource characteristics and institutional attributes, were major factors affecting participation in decision-making and forest management. However, the number of international migrants did not have a significant role in determining the levels of the participation. This study provides valuable insights for future community forestry policymaking that aims to address the effects of out-migration on community forest management in Nepal.more » « less
-
Changes driven by both unanticipated human activities and management actions are creating wicked management landscapes in freshwater and marine ecosystems that require new approaches to support decision-making. By linking a predictive model of nutrient- and temperature-driven bottom hypoxia with observed commercial fishery harvest data from Lake Erie (United States–Canada) over the past century (1928–2022) and climate projections (2030–2099), we show how simple, yet robust models and routine monitoring data can be used to identify tradeoffs associated with nutrient management and guide decision-making in even the largest of aquatic ecosystems now and in the future. Our approach enabled us to assess planned nutrient load reduction targets designed to mitigate nutrient-driven hypoxia and show why they appear overly restrictive based on current fishery needs, indicating tradeoffs between water quality and fisheries management goals. At the same time, our temperature results show that projected climate change impacts on hypoxic extent will require more stringent nutrient regulations in the future. Beyond providing a rare example of bottom hypoxia driving changes in fishery harvests at an ecosystem scale, our study illustrates the need for adaptive ecosystem–based management, which can be informed by simple predictive models that can be readily applied over long time periods, account for tradeoffs across multiple management sectors (e.g., water quality, fisheries), and address ecosystem nonstationarity (e.g., climate change impacts on management targets). Such approaches will be critical for maintaining valued ecosystem services in the many aquatic systems worldwide that are vulnerable to multiple drivers of environmental change.more » « less
-
null (Ed.)Predictions from species distribution models (SDMs) are commonly used in support of environmental decision-making to explore potential impacts of climate change on biodiversity. However, because future climates are likely to differ from current climates, there has been ongoing interest in understanding the ability of SDMs to predict species responses under novel conditions (i.e., model transferability). Here, we explore the spatial and environmental limits to extrapolation in SDMs using forest inventory data from 11 model algorithms for 108 tree species across the western United States. Algorithms performed well in predicting occurrence for plots that occurred in the same geographic region in which they were fitted. However, a substantial portion of models performed worse than random when predicting for geographic regions in which algorithms were not fitted. Our results suggest that for transfers in geographic space, no specific algorithm was better than another as there were no significant differences in predictive performance across algorithms. There were significant differences in predictive performance for algorithms transferred in environmental space with GAM performing best. However, the predictive performance of GAM declined steeply with increasing extrapolation in environmental space relative to other algorithms. The results of this study suggest that SDMs may be limited in their ability to predict species ranges beyond the environmental data used for model fitting. When predicting climate-driven range shifts, extrapolation may also not reflect important biotic and abiotic drivers of species ranges, and thus further misrepresent the realized shift in range. Future studies investigating transferability of process based SDMs or relationships between geodiversity and biodiversity may hold promise.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/ffgc.2020.587178
