The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of neural functionality, software abstraction levels, and hardware devices, yet are typically not suitable for rapid prototyping or application to problems in the domain of machine learning. In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared toward machine learning and reinforcement learning. Our software, called 1, enables rapid building and simulation of spiking networks and features user-friendly, concise syntax. is built on the deep neural networks library, facilitating the implementation of spiking neural networks on fast CPU and GPU computational platforms. Moreover, the framework can be adjusted to utilize other existing computing and hardware backends; e.g., and . We provide an interface with the OpenAI library, allowing for training and evaluation of spiking networks on reinforcement learning environments. We argue that this package facilitates the use of spiking networks for large-scale machine learning problems and show some simple examples by using in practice.
Abstract. There is a growing recognition among water resource managers that sustainable watershed management needs to not only account for the diverse ways humans benefit from the environment, but also incorporate the impact of human actions on the natural system. Coupled naturalhuman system modeling through explicit modeling of both natural and human behavior can help reveal the reciprocal interactions and co-evolution of the natural and human systems. This study develops a spatially scalable, generalized agent-based modeling (ABM) framework consisting of a process-based semi-distributed hydrologic model (SWAT) and a decentralized water system model to simulate the impacts of water resource management decisions that affect the food-water-energy-environment (FWEE) nexus at a watershed scale. Agents within a river basin are geographically delineated based on both political and watershed boundaries and represent key stakeholders of ecosystem services. Agents decide about the priority across three primary water uses: food production, hydropower generation and ecosystem health within their geographical domains. Agents interact with the environment (streamflow) through the SWAT model and interact with other agents through a parameter representing willingness to cooperate. The innovative twoway coupling between the water system model and SWAT enables this framework to fully explore the feedback of human decisions on the environmental dynamics and vice versa. To support non-technical stakeholder interactions, a web-based user interface has been developed that allows for role-play and participatory modeling. The generalized ABM framework is also tested in two key transboundary river basins, the Mekong River basin in Southeast Asia and the Niger River basin in West Africa, where water uses for ecosystem health compete with growing human demands on food and energy resources. We present modeling results for crop production, energy generation and violation of ecohydrological indicators at both the agent and basin-wide levels to shed light on holistic FWEE management policies in these two basins.
Water, food, energy, and the ecosystems they depend on interact with each other in highly complex and interlinked ways. These interdependencies can be traced particularly well in the context of a river basin, which is delineated by hydrological boundaries. The interactions are shaped by humans interacting with nature, and as such, a river basin can be characterized as a complex, coupled socioecological system. The Niger River Basin in West Africa is such a system, where water infrastructure development to meet growing water, food, and energy demands may threaten a productive and vulnerable basin ecosystem. These dynamic interactions remain poorly understood. Trade‐off analyses between different sectors and at different spatial scales are needed to support solution‐oriented policy analysis, particularly in transboundary basins. This study assesses the impact of climate and human/anthropogenic changes on the water, energy, food, and ecosystem sectors and characterizes the resulting trade‐offs through a set of generic metrics related to the sustainability of water availability. Results suggest that dam development can mitigate negative impacts from climate change on hydropower generation and also on ecosystem health to some extent.
Incentive‐based policies, such as the cap‐and‐trade system, have been shown to be useful in the context of groundwater management. This study compares the performance of a groundwater market with water quotas when assumptions of perfect information are violated due to climate change and hydrogeologic heterogeneity and explores how changes in future climate affect market performance. A subbasin of the Republican River Basin, overlying the Ogallala aquifer in the High Plains of the United States, is used as a case study. Building on a previously developed model, a multiagent system model simulating a groundwater market is developed where self‐interested agents can trade water use permits to maximize individual benefits subject to irrigation and land constraints. This economic model is coupled with a calibrated physically based groundwater model for the study region that allows for an evaluation of streamflow depletion impacts, which has been the focus of management efforts in the basin. Results show that trading of permits between farmers results in increased economic benefits and, in some cases, reduced environmental violations. However, the benefits of a groundwater market are distributed unequally resulting in “winners” and “losers” across the system. Future changes in climate are shown to significantly influence farmers willingness to pay for groundwater and thus increase the variation in groundwater price and pumping. These findings emphasize the importance of addressing hydroclimatologic variability and change in the design of groundwater markets.
There has recently been a return in climate change risk management practice to bottom‐up, robustness‐based planning paradigms introduced 40 years ago. The World Bank's decision tree framework (DTF) for “confronting climate uncertainty” is one incarnation of those paradigms. In order to better represent the state of the art in climate change risk assessment and evaluation techniques, this paper proposes: (1) an update to the DTF, replacing its “climate change stress test” with a multidimensional stress test; and (2) the addition of a Bayesian network framework that represents joint probabilistic behavior of uncertain parameters as sensitivity factors to aid in the weighting of scenarios of concern (the combination of conditions under which a water system fails to meet its performance targets). Using the updated DTF, water system planners and project managers would be better able to understand the relative magnitudes of the varied risks they face, and target investments in adaptation measures to best reduce their vulnerabilities to change. Next steps for the DTF include enhancements in: modeling of extreme event risks; coupling of human‐hydrologic systems; integration of surface water and groundwater systems; the generation of tradeoffs between economic, social, and ecological factors; incorporation of water quality considerations; and interactive data visualization.
Water-related hazards such as floods, droughts, and disease cause damage to an economy through the destruction of physical capital including property and infrastructure, the loss of human capital, and the interruption of economic activities, like trade and education. The question for policy makers is whether the impacts of water-related risk accrue to manifest as a drag on economic growth at a scale suggesting policy intervention. In this study, the average drag on economic growth from water-related hazards faced by society at a global level is estimated. We use panel regressions with various specifications to investigate the relationship between economic growth and hydroclimatic variables at the country-river basin level. In doing so, we make use of surface water runoff variables never used before. The analysis of the climate variables shows that water availability and water hazards have significant effects on economic growth, providing further evidence beyond earlier studies finding that precipitation extremes were at least as important or likely more important than temperature effects. We then incorporate a broad set of variables representing the areas of infrastructure, institutions, and information to identify the characteristics of a region that determine its vulnerability to water-related risks. The results identify water scarcity, governance, and agricultural intensity as the most relevant measures affecting vulnerabilities to climate variability effects.
The importance of green water (moisture from rain stored in soils) for global food and water security is widely recognized, with process-based simulation models and field-level studies demonstrating its role in supporting rainfed agriculture. Despite this evidence, the relationship between green water anomalies and rainfed agriculture has not yet been investigated using statistical models that identify a causal relationship between the variables. Here, we address this gap and use disaggregated statistical regression (panel data analysis) at the 30 arc-min grid level to study the response of observed yields of four main crops (maize, rice, soybean and wheat) to green water anomalies globally over rainfed areas. Dry green water anomalies (1 or 2 standard deviations below long-term average) decrease rainfed crop yields worldwide. This effect is more pronounced for wheat and maize, whose yields decline by 12%-18% and 7%-12% respectively. Globally, agricultural production benefits from wet green water anomalies. This effect is intensified in arid climates and weakened in humid climates where, for wheat, soybean and rice, periods of green water availability 2 standard deviations above long-term averages lead to declines in crop yield. This confirms existing evidence that excess soil moisture is detrimental to crop yield. These findings (1) advance our understanding of the impact of green water on rainfed food production and (2) provide empirical evidence supporting arguments for better management of local green water resources to reduce the impact of agricultural drought and waterlogging on rainfed crop production and capture the yield increasing effects of positive green water anomalies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.