Advances in remote sensing and machine learning enable increasingly accurate, inexpensive, and timely estimation of poverty and malnutrition indicators to guide development and humanitarian agencies’ programming. However, state of the art models often rely on proprietary data and/or deep or transfer learning methods whose underlying mechanics may be challenging to interpret. We demonstrate how interpretable random forest models can produce estimates of a set of (potentially correlated) malnutrition and poverty prevalence measures using free, open access, regularly updated, georeferenced data. We demonstrate two use cases: contemporaneous prediction, which might be used for poverty mapping, geographic targeting, or monitoring and evaluation tasks, and a sequential nowcasting task that can inform early warning systems. Applied to data from 11 low and lower-middle income countries, we find predictive accuracy broadly comparable for both tasks to prior studies that use proprietary data and/or deep or transfer learning methods.

Context In Queensland, the management of estuarine crocodiles (Crocodylus porosus) by the government is important for ensuring public safety, especially along the populated east coast, where there is a large human population. Aims The present study aimed to determine historical, temporal and spatial patterns of human–crocodile conflict in Queensland. Methods The study used Queensland Government records of estuarine crocodile attacks (1971–2015), sightings by the general public (2003–2015), and removals and relocations for management purposes (1985–2015) to develop General Linear Models describing historical, temporal and spatial patterns. Key results The highest number of attacks, sightings, removals and relocations occurred along the populated east coast between Townsville and the Daintree during wet season months (November–February). There have been 35 crocodile attacks in Queensland since 1971 (total 0.8 per year; fatal 0.3 per year), mostly involving local people or regular visitors (77.1%), specifically adult males (71.4%; mean age 44). There has been an increase in the rate of crocodile attacks over time, with an average of 1.3 per year since 1996, most of which were non-fatal (84%). The number of crocodile sightings has been increasing annually (with a mean of 348 per year since 2011), while the number of crocodiles removed or relocated for management purposes (n = 608) has fluctuating widely each year (range 1–57). Conclusions The level of human–crocodile conflict in Queensland is increasing, and this is likely to be a consequence of increasing human and crocodile populations. While conflict is highest during the wet season, estuarine crocodiles pose a threat to public safety year round. Implications With the increase in conflict, the ongoing management of estuarine crocodiles, through targeted removals in and around areas of higher human habitation and through education, is essential for ensuring public safety into the future.