Surya Karthik Mukkavilli

Reinforcement learning is emerging as a powerful tool for microrobots control, as it enables autonomous navigation in environments where classical control approaches fall short. However, applying reinforcement learning to microrobotics is difficult due to the need for large training datasets, the slow convergence in physical systems and poor generalizability across environments. These challenges are amplified in ultrasound-actuated microrobots, which require rapid, precise adjustments in high-dimensional action space, which are often too complex for human operators. Addressing these challenges requires sample-efficient algorithms that adapt from limited data while managing complex physical interactions. To meet these challenges, we implemented model-based reinforcement learning for autonomous control of an ultrasound-driven microrobot, which learns from recurrent imagined environments. Our non-invasive, AI-controlled microrobot offers precise propulsion and efficiently learns from images in data-scarce environments. On transitioning from a pretrained simulation environment, we achieved sample-efficient collision avoidance and channel navigation, reaching a 90% success rate in target navigation across various channels within an hour of fine-tuning. Moreover, our model initially generalized successfully in 50% of tasks in new environments, improving to over 90% with 30 min of further training. We further demonstrated real-time manipulation of microrobots in complex vasculatures under both static and flow conditions, thus underscoring the potential of AI to revolutionize microrobotics in biomedical applications.

A natural hazard event that highly impacted a society might trigger a wave of post-disaster research analysis, which looks into the cause of the disaster, the types of impact, or any lessons learned to prevent similar events in the future. In short, post-disaster research contains valuable knowledge that should be utilized in disaster risk management. However, in the past 70 years, the scientific community published around 600,000 articles on hydro-hazards, such as floods, droughts, and landslides. Finding articles that describe specific disaster events and synthesizing their knowledge is not humanly possible anymore due to near exponentially increasing numbers of publications. However, recent advancements in large language models allow the analysis and extraction of described disaster events in the scientific literature.Here we make use of the Wealth over Woe scientific abstract dataset (Stein et al. 2024), with abstracts that were automatically annotated for hydro-hazards and geolocation. It allows us to track publication trends and to identify disaster events that triggered a wave of new research. We additionally make use of the large language model Llama 70B to extract specific hazard events mentioned in each abstract (e.g. 2003 summer drought in Europe, Pakistan flood in 2010, 2002 Elbe flood, etc.) as well as other described details surrounding the event.While we know that hydro-hazard research is biased against low-income countries, exceptional disaster events can shift research priorities for several years. The additional funding can support valuable local post-disaster research. The named event recognition can therefore help us answer questions such as: What kind of hydro-hazards are studied in detail and where? What are the key research foci for post-disaster analysis? And are there regional differences to these answers?

AI has catalyzed transformative advancements across multiple sectors, from medical diagnostics to autonomous vehicles, enhancing precision and efficiency. As it ventures into microrobotics, AI offer innovative solutions to the formidable challenge of controlling and manipulating microrobots, which typically operate within imprecise, remotely actuated systems—a task often too complex for human operators. We implement state-of-the-art model-based reinforcement learning for autonomous control of an ultrasound-driven microrobot learning from recurrent imagined environments. Our non-invasive, AI-controlled microrobot offers precise propulsion, which efficiently learns from images in data-scarce environments. Transitioning from a pre-trained simulation environment, we achieve sample-efficient collision avoidance and channel navigation, reaching a 90% success rate in target navigation across various channels within an hour of fine-tuning. Moreover, our model initially successfully generalized in 50% of tasks in new environments, improving to over 90% with 30 minutes of further training. Furthermore, we have showcased real-time manipulation of microrobots within complex vasculatures and across stationary and physiological flows, underscoring AI’s potential to revolutionize microrobotics in biomedical applications, potentially transforming medical procedures.

Increasing publication numbers make it difficult to keep up with knowledge evolution in a science like hydrology. Here we give recommendations to authors and journals for writing future‐proof articles that contribute to knowledge accumulation and synthesis.

The report recommends that: 1) Policymakers should conduct holistic assessments of social, economic, and cultural factors before AI adoption in the water sector, as prospective applications of AI are case- specific. It is also important to conduct baseline studies to measure the implementation capacity, return on investment, and impact of intervention. 2) To ensure positive development outcomes, policies regarding the use of AI for water-related challenges should be coupled with capacity and infrastructure development policies. Capacity development policies need to address the AI and Information and Communications Technology (ICT) needs for the AI-related skill development of all water-related stakeholders. Infrastructure development policies should address the underlying requirements of computation, energy, data generation, and storage. The sequencing of these policies is critical. 3) To mitigate the predicted job displacement that will accompany AI-led innovation in the water sector, policies should direct investments towards enabling a skilled workforce by developing water sector-related education at all levels. This skilled workforce should be strategically placed to offset dependency on the private sector. 4) Water-related challenges are cross-cutting running from grassroots to the global level and require an understanding of the water ecosystem. It is important for countries connected by major rivers and watersheds to collaborate in developing policies that advance the use of AI to address common water-related challenges. 5) A council or agency with representation from all stakeholders should be constituted at the national level, to allow for the successful adoption of AI by water agencies. This council or agency should be tasked with the development of policies, guidelines, and codes of conduct for the adoption of AI in the water-sector. These key policy recommendations can be used as primary guidelines for the development of strategies and plans to use AI to help achieve water-related SDGs.

Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against ground truth. Biases identified with the NASA Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) aerosol optical depth (AOD) dataset, against the Aerosol Robotic Network (AERONET) ground measurements in previous studies, motivated the development of a deep learning based AOD prediction model globally. This study combines a convolutional neural network (CNN) with MERRA-2, tested against all AERONET sites. The new hybrid CNN-based model provides better estimates validated versus AERONET ground truth, than only using MERRA-2 reanalysis.