Emerging technologies associated with Artificial Intelligence (AI) have enabled improvements in global food security situations. However, there is a limited understanding regarding the extent to which stakeholders are involved in AI modelling research for food security purposes. This study systematically reviews the existing literature to bridge the knowledge gap in AI and food security, focusing on software modelling perspectives. The study found the application of AI models to examine various indicators of food security across six continents, with most studies conducted in sub-Saharan Africa. While research organisations conducting AI modelling were predominantly based in Europe or the Americas, their study communities were in the Global South. External funders also supported AI modelling research on food security through international universities and research institutes, although some collaborations with local organisations and external partners were identified. The analysis revealed three patterns in the application of AI models for food security research: (1) the exclusive utilisation of AI models to assess food security situations, (2) stakeholder involvement in some aspects of the AI modelling process, and (3) stakeholder involvement in AI modelling for food security through an iterative process. Overall, studies on AI models for food security were primarily experimental and lacked real-life implementation of the results with stakeholders. Consequently, this study concluded that research on AI, which incorporates feedback and/or the implementation of research outcomes for stakeholders, can contribute to learning and enhance the validity of the models in addressing food security challenges.

The current trend towards living in big cities contributes to an increased demand for efficient and sustainable space and resource allocation in urban environments. This leads to enormous pressure for resource minimization in city planning. One pillar of efficient city management is a smart intermodal traffic system. Planning and organizing the various kinds of modes of transport in a complex and dynamically adaptive system such as a city is inherently challenging. By deliberately simplifying reality, models can help decision-makers shape the traffic systems of tomorrow. Meanwhile, Smart City initiatives are investing in sensors to observe and manage many kinds of urban resources, making up a part of the Internet of Things (IoT) that produces massive amounts of data relevant for urban planning and monitoring. We use these new data sources of smart cities by integrating real-time data of IoT sensors in an ongoing simulation. In this sense, the model is a digital twin of its real-world counterpart, being augmented with real-world data. To our knowledge, this is a novel instance of real-time correction during simulation of an agent-based model. The process of creating a valid mapping between model components and real-world objects posed several challenges and offered valuable insights, particularly when studying the interaction between humans and their environment. As a proof-of-concept for our implementation, we designed a showcase with bike rental stations in Hamburg-Harburg, a southern district of Hamburg, Germany. Our objective was to investigate the concept of real-time data correction in agent-based modeling, which we consider to hold great potential for improving the predictive capabilities of models. In particular, we hope that the chosen proof-of-concept informs the ongoing politically supported trends in mobility—away from individual and private transport and towards—in Hamburg.

Due to the fact that the South Africa’s savanna landscapes are under changing conditions, the previously sustainable firewood collection system in rural areas has become a social-ecological factor in questions about landscape management. While the resilience of savannas in national parks such as Kruger National Park (KNP) in South Africa has been widely acknowledged in ecosystem management, the resilience of woody vegetation outside protected areas has been underappreciated. Collecting wood is the dominant source of energy for rural households, and there is an urgent need for land management to find sustainable solutions for this complex social-ecological system. However, the firewood collection scenario is only one example, and stands for all “human-ecosystem service” interactions under the topic of over-utilization, e.g., fishery, grazing, harvesting. Agent-based modeling combined with goal-oriented action planning (GOAP) can provide fresh insights into the relationship between individual needs of humans and changes in land use. At the same time, this modeling approach includes adaptive behavior under changing conditions. A firewood collection scenario was selected for a proof-of-concept comprising households, collectors, ecosystem services and firewood sites. Our results have shown that, even when it is predictable what a single human agent will do, massive up-scaling is needed in order to understand the whole complexity of social-ecological systems. Under changing conditions, such as climate and an increasing population, fair distribution of natural goods become an important issue.

Models can provide valuable decision support in the ongoing effort to create a sustainable and effective modality mix in urban settings. Modern transportation infrastructures must meaningfully combine public transport with other mobility initiatives such as shared and on-demand systems. The increase of options and possibilities in multi-modal travel implies an increase in complexity when planning and implementing such an infrastructure. Multi-agent systems are well-suited for addressing questions that require an understanding of movement patterns and decision processes at the individual level. Such models should feature intelligent software agents with flexible internal logic and accurately represent the core functionalities of new modalities. We present a model in which agents can choose between owned modalities, station-based bike sharing modalities, and free-floating car sharing modalities as they exit the public transportation system and seek to finish their personal multi-modal trip. Agents move on a multi-modal road network where dynamic constraints in route planning are evaluated based on an agent’s query. Modality switch points (MSPs) along the route indicate the locations at which an agent can switch from one modality to the next (e.g., a bike rental station to return a used rental bike and continue on foot). The technical implementation of MSPs within the road network was a central focus in this work. To test their efficacy in a controlled experimental setting, agents optimized only the travel time of their multi-modal routes. However, the functionalities of the model enable the implementation of different optimization criteria (e.g., financial considerations or climate neutrality) and unique agent preferences as well. Our findings show that the implemented MSPs enable agents to switch between modalities at any time, allowing for the kind of versatile, individual, and spontaneous travel that is common in modern multi-modal settings.

International policy and humanitarian guidance emphasize the need for precise, subnational malaria risk assessments with cross-regional comparability. Spatially explicit indicator-based assessments can support humanitarian aid organizations in identifying and localizing vulnerable populations for scaling resources and prioritizing aid delivery. However, the reliability of these assessments is often uncertain due to data quality issues. This article introduces a data evaluation framework to assist risk modelers in evaluating data adequacy. We operationalize the concept of “data adequacy” by considering “quality by design” (suitability) and “quality of conformance” (reliability). Based on a use case we developed in collaboration with Médecins Sans Frontières, we assessed data sources popular in spatial malaria risk assessments and related domains, including data from the Malaria Atlas Project, a healthcare facility database, WorldPop population counts, Climate Hazards group Infrared Precipitation with Stations (CHIRPS) precipitation estimates, European Centre for Medium-Range Weather Forecasts (ECMWF) precipitation forecast, and Armed Conflict Location and Event Data Project (ACLED) conflict events data. Our findings indicate that data availability is generally not a bottleneck, and data producers effectively communicate contextual information pertaining to sources, methodology, limitations and uncertainties. However, determining such data’s adequacy definitively for supporting humanitarian intervention planning remains challenging due to potential inaccuracies, incompleteness or outdatedness that are difficult to quantify. Nevertheless, the data hold value for awareness raising, advocacy and recognizing trends and patterns valuable for humanitarian contexts. We contribute a domain-agnostic, systematic approach to geodata adequacy evaluation, with the aim of enhancing geospatial risk assessments, facilitating evidence-based decisions.