Manual assessment of flower abundance of different flowering plant species in grasslands is a time consuming process. We present an automated approach to determine the flower abundance in grasslands from drone images using a deep learning (Faster R-CNN) object detection approach, which is trained and evaluated on data of five flights and two sites. Our deep learning network is able to identify and classify individual flowers. The novel method allows generating spatially explicit maps of flower abundance that meets or exceeds the accuracy of the manually counted extrapolation method and is less labor intensive. The results are very good for some types of flowers with precision and recall being close to or higher than $90\ \%$. Other flowers are detected poorly due to reasons such as lack of enough training data, appearance changes due to phenology or flowers being too small to be reliably distinguishable on the aerial images. The method is able to give precise estimates of the abundance of many flowering plant species. The collection of more training data will allow better predictions in the future for the flowers that are not well predicted yet. The developed pipeline can be applied to any sort of aerial object detection problems.

1. The foraging and nesting performance of bees can provide important information on bee health and is of interest for risk and impact assessment of environmental stressors. While radio-frequency identification (RFID) technology is an efficient tool increasingly used for the collection of behavioral data in social bee species such as honey bees, behavioral studies on solitary bees still largely depend on direct observations, which is very time-consuming. 2. Here, we present a novel automated methodological approach of individually and simultaneously tracking and analyzing foraging and nesting behavior of numerous cavity-nesting solitary bees. The approach consists of monitoring nesting units by video recording and automated analysis of videos by a machine learning based software. This Bee Tracker software consists of four trained deep learning networks to detect bees that enter or leave their nest and to recognize individual IDs on the bees’ thorax as well as the IDs of their nests according to their positions in the nesting unit. 3. The software is able to identify each nest of each individual nesting bee, which permits to measure individual-based measures of reproductive success. Moreover, the software quantifies the number of cavities a female enters until it finds its nest as a proxy of nest recognition, and it provides information on the number and duration of foraging trips. By training the software on 8 videos recording 24 nesting females per video, the software achieved a precision of 96% correct measurements of these parameters. 4. The software could be adapted to various experimental setups by training it to an according set of videos. The presented method allows to efficiently collect large amounts of data on cavity-nesting solitary bee species and represents a promising new tool for the monitoring and assessment of behavior and reproductive success under laboratory, semi-field and field conditions.