Search

Abstract The development of anthropic activities and climate change effects impact worldwide species' ecosystems and habitats. Habitats' adequate prediction can be an important tool to assess current and future trends. In addition, it allows strategies development for their conservation. The Neltuma pallida of the forest region in northern Peru, although very significant, has experienced a decline in recent years. The objective of this research is to evaluate the current and future distribution and conservation status of N. pallida in the Peruvian dry forest under climate change (Location: Republic of Peru). A total of 132 forest presence records and 10 variables (bioclimatic, topographic, and soil) were processed and selected to obtain the current and future distribution for 2100, using Google Earth Engine (GEE), RStudio, and MaxEnt. The area under the curve values fell within the range of 0.93–0.95, demonstrating a strong predictive capability for both present and future potential habitats. The findings indicated that the likely range of habitats for N. pallida was shaped by factors such as the average temperature of wettest quarter, maximum temperature of warmest month, elevation, rainfall, and precipitation of driest month. The main suitable areas were in the central regions of the geographical departments of Tumbes, Piura, and Lambayeque, as well as in the northern part of La Libertad. It is critical to determine the habitat suitability of plant species for conservation managers since this information stimulates the development of policies that favor sustainable use programs. In addition, these results can contribute significantly to identify new areas for designing strategies for populations conserving and recovering with an ecological restoration approach.

The spatial heterogeneity of soil properties has a significant impact on crop growth, making it difficult to adopt site-specific crop management practices. Traditional laboratory-based analyses are costly, and data extrapolation for mapping soil properties using high-resolution imagery becomes a computationally expensive procedure, taking days or weeks to obtain accurate results using a desktop workstation. To overcome these challenges, cloud-based solutions such as Google Earth Engine (GEE) have been used to analyze complex data with machine learning algorithms. In this study, we explored the feasibility of designing and implementing a digital soil mapping approach in the GEE platform using high-resolution reflectance imagery derived from a thermal infrared and multispectral camera Altum (MicaSense, Seattle, WA, USA). We compared a suite of multispectral-derived soil and vegetation indices with in situ measurements of physical-chemical soil properties in agricultural lands in the Peruvian Mantaro Valley. The prediction ability of several machine learning algorithms (CART, XGBoost, and Random Forest) was evaluated using R2, to select the best predicted maps (R2 > 0.80), for ten soil properties, including Lime, Clay, Sand, N, P, K, OM, Al, EC, and pH, using multispectral imagery and derived products such as spectral indices and a digital surface model (DSM). Our results indicate that the predictions based on spectral indices, most notably, SRI, GNDWI, NDWI, and ExG, in combination with CART and RF algorithms are superior to those based on individual spectral bands. Additionally, the DSM improves the model prediction accuracy, especially for K and Al. We demonstrate that high-resolution multispectral imagery processed in the GEE platform has the potential to develop soil properties prediction models essential in establishing adaptive soil monitoring programs for agricultural regions.