Unmanned aerial vehicle images in the machine learning for agave detection.

In this study, six supervised classification algorithms were compared. The algorithms were based on cluster analysis, distance, deep learning, and object-based image analysis. Our objective was to determine which of these algorithms has the highest overall accuracy in both detection and automated estimation of agave cover in a given area to help growers manage their plantations. An orthomosaic with a spatial resolution of 2.5 cm was derived from 300 images obtained with a DJI Inspire 1 unmanned aerial system. Two training classes were defined: (1) sites where the presence of agaves was identified and (2) "absence" where there were no agaves but other plants were present. The object-oriented algorithm was found to have the highest overall accuracy (0.963), followed by the support-vector machine with 0.928 accuracy and the neural network with 0.914. The algorithms with statistical criteria for classification were the least accurate: Mahalanobis distance = 0.752 accuracy and minimum distance = 0.421. We further recommend that the object-oriented algorithm be used, because in addition to having the highest overall accuracy for the image segmentation process, it yields parameters that are useful for estimating the coverage area, size, and shapes, which can aid in better selection of agave individuals for harvest.

Waterhole detection using a vegetation index in desert bighorn sheep (Ovis canadensis cremnobates) habitat.

In arid ecosystems, desert bighorn sheep are dependent on natural waterholes, particularly in summer when forage is scarce and environmental temperatures are high. To detect waterholes in Sierra Santa Isabel, which is the largest area of desert bighorn sheep habitat in the state of Baja California, Mexico, we used the normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) from Sentinel-2 satellite images. Waterhole detection was based on the premise that sites with greater water availability, where NDVI was higher, can be identified by their density of vegetation greenness. For the detected waterholes, we estimated the escape terrain (presence of cliffs or steep, rocky slopes) around each by the vector ruggedness measure to determine their potential use by desert bighorn sheep based on the animals' presence as documented by camera traps. We detected 14 waterholes with the NDVI of which 11 were known by land owners and 3 were unrecorded. Desert bighorn were not detected in waterholes with high values of escape terrain, i.e., flat areas. Waterhole detection by NDVI is a simple method, and with the assistance and knowledge of the inhabitants of the Sierra, it was possible to confirm the presence each waterhole in the field.

Predicting Pinus monophylla forest cover in the Baja California Desert by remote sensing.

The Californian single-leaf pinyon (Pinus monophylla var. californiarum), a subspecies of the single-leaf pinyon (the world's only one-needled pine), inhabits semi-arid zones of the Mojave Desert (southern Nevada and southeastern California, US) and also of northern Baja California (Mexico). This tree is distributed as a relict subspecies, at elevations of between 1,010 and 1,631 m in the geographically isolated arid Sierra La Asamblea, an area characterized by mean annual precipitation levels of between 184 and 288 mm. The aim of this research was (i) to estimate the distribution of P. monophylla var. californiarum in Sierra La Asamblea by using Sentinel-2 images, and (ii) to test and describe the relationship between the distribution of P. monophylla and five topographic and 18 climate variables. We hypothesized that (i) Sentinel-2 images can be used to predict the P. monophylla distribution in the study site due to the finer resolution (×3) and greater number of bands (×2) relative to Landsat-8 data, which is publically available free of charge and has been demonstrated to be useful for estimating forest cover, and (ii) the topographical variables aspect, ruggedness and slope are particularly important because they represent important microhabitat factors that can determine the sites where conifers can become established and persist. An atmospherically corrected a 12-bit Sentinel-2A MSI image with 10 spectral bands in the visible, near infrared, and short-wave infrared light region was used in combination with the normalized differential vegetation index (NDVI). Supervised classification of this image was carried out using a backpropagation-type artificial neural network algorithm. Stepwise multiple linear binominal logistical regression and Random Forest classification including cross validation were used to model the associations between presence/absence of P. monophylla and the five topographical and 18 climate variables. Using supervised classification of Sentinel-2 satellite images, we estimated that P. monophylla covers 6,653 ± 319 ha in the isolated Sierra La Asamblea. The NDVI was one of the variables that contributed most to the prediction and clearly separated the forest cover (NDVI > 0.35) from the other vegetation cover (NDVI < 0.20). Ruggedness was the most influential environmental predictor variable, indicating that the probability of occurrence of P. monophylla was greater than 50% when the degree of ruggedness terrain ruggedness index was greater than 17.5 m. The probability of occurrence of the species decreased when the mean temperature in the warmest month increased from 23.5 to 25.2 °C. Ruggedness is known to create microclimates and provides shade that minimizes evapotranspiration from pines in desert environments. Identification of the P. monophylla stands in Sierra La Asamblea as the most southern populations represents an opportunity for research on climatic tolerance and community responses to climate variability and change.