Preprints

Translating global commitments to protect and restore nature into context-specific action remains difficult. Earth-system functions, including carbon storage, erosion regulation and pollination, are spatially heterogeneous, legacy-rich and rarely captured by a single global indicator. [...]

We present a hardware-efficient hybrid trigger for FPGA-based radio detection of extensive air showers. The hybrid design consists of a lightweight denoiser that cleans raw ADC traces anda compact classifier that operates on the denoised output, enabling robust near-threshold pulse detection in high-interference environments. [...]

Since the first development of hectometre-scale soil moisture estimation using epithermal neutron intensity from moderated Cosmic-Ray Neutron Sensors (CRNS), researchers have hypothesize that concurrent lower‑energy, thermal neutron measurements with bare (unmoderated) detectors could also be useful for environmental sensing. Early studies in this field have highlighted the potential of thermal neutrons for monitoring biomass, plant traits, and snow water equivalent, while others underlined a soil moisture dependence that can adversely affect their usability. [...]

Data editing with generative methods typically requires differentiable objectives and gradient-based search. However, these assumptions break down in flow-based settings, where edits are performed through forward and backward integration and often involve non-differentiable or black-box objectives. [...]

Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback. A key difficulty is improving observed behavior without extrapolating beyond what the offline data supports. [...]