Classification of riparian forest species and health condition using multi-temporal and hyperspatial imagery from unmanned aerial system.

Riparian forests are critically endangered many anthropogenic pressures and natural hazards. The importance of riparian zones has been acknowledged by European Directives, involving multi-scale monitoring. The use of this very-high-resolution and hyperspatial imagery in a multi-temporal approach is an emerging topic. The trend is reinforced by the recent and rapid growth of the use of the unmanned aerial system (UAS), which has prompted the development of innovative methodology. Our study proposes a methodological framework to explore how a set of multi-temporal images acquired during a vegetative period can differentiate some of the deciduous riparian forest species and their health conditions. More specifically, the developed approach intends to identify, through a process of variable selection, which variables derived from UAS imagery and which scale of image analysis are the most relevant to our objectives.The methodological framework is applied to two study sites to describe the riparian forest through two fundamental characteristics: the species composition and the health condition. These characteristics were selected not only because of their use as proxies for the riparian zone ecological integrity but also because of their use for river management.The comparison of various scales of image analysis identified the smallest object-based image analysis (OBIA) objects (ca. 1 m(2)) as the most relevant scale. Variables derived from spectral information (bands ratios) were identified as the most appropriate, followed by variables related to the vertical structure of the forest. Classification results show good overall accuracies for the species composition of the riparian forest (five classes, 79.5 and 84.1% for site 1 and site 2). The classification scenario regarding the health condition of the black alders of the site 1 performed the best (90.6%).The quality of the classification models developed with a UAS-based, cost-effective, and semi-automatic approach competes successfully with those developed using more expensive imagery, such as multi-spectral and hyperspectral airborne imagery. The high overall accuracy results obtained by the classification of the diseased alders open the door to applications dedicated to monitoring of the health conditions of riparian forest. Our methodological framework will allow UAS users to manage large imagery metric datasets derived from those dense time series.

Discrimination of Deciduous Tree Species from Time Series of Unmanned Aerial System Imagery.

Technology advances can revolutionize Precision Forestry by providing accurate and fine forest information at tree level. This paper addresses the question of how and particularly when Unmanned Aerial System (UAS) should be used in order to efficiently discriminate deciduous tree species. The goal of this research is to determine when is the best time window to achieve an optimal species discrimination. A time series of high resolution UAS imagery was collected to cover the growing season from leaf flush to leaf fall. Full benefit was taken of the temporal resolution of UAS acquisition, one of the most promising features of small drones. The disparity in forest tree phenology is at the maximum during early spring and late autumn. But the phenology state that optimized the classification result is the one that minimizes the spectral variation within tree species groups and, at the same time, maximizes the phenologic differences between species. Sunlit tree crowns (5 deciduous species groups) were classified using a Random Forest approach for monotemporal, two-date and three-date combinations. The end of leaf flushing was the most efficient single-date time window. Multitemporal datasets definitely improve the overall classification accuracy. But single-date high resolution orthophotomosaics, acquired on optimal time-windows, result in a very good classification accuracy (overall out of bag error of 16%).

Unmanned aerial survey of elephants.

The use of a UAS (Unmanned Aircraft System) was tested to survey large mammals in the Nazinga Game Ranch in the south of Burkina Faso. The Gatewing ×100™ equipped with a Ricoh GR III camera was used to test animal reaction as the UAS passed, and visibility on the images. No reaction was recorded as the UAS passed at a height of 100 m. Observations, made on a set of more than 7000 images, revealed that only elephants (Loxodonta africana) were easily visible while medium and small sized mammals were not. The easy observation of elephants allows experts to enumerate them on images acquired at a height of 100 m. We, therefore, implemented an aerial strip sample count along transects used for the annual wildlife foot count. A total of 34 elephants were recorded on 4 transects, each overflown twice. The elephant density was estimated at 2.47 elephants/km(2) with a coefficient of variation (CV%) of 36.10%. The main drawback of our UAS was its low autonomy (45 min). Increased endurance of small UAS is required to replace manned aircraft survey of large areas (about 1000 km of transect per day vs 40 km for our UAS). The monitoring strategy should be adapted according to the sampling plan. Also, the UAS is as expensive as a second-hand light aircraft. However the logistic and flight implementation are easier, the running costs are lower and its use is safer. Technological evolution will make civil UAS more efficient, allowing them to compete with light aircraft for aerial wildlife surveys.