A red clover coverage prediction method using drones and deep learning was developed. Six images of a grass-legume mixed swards were used as the training dataset and 180 images (60 test plots taken three times) as the estimation images. CNN models were created using three CNN architectures (InceptionV3, ResNet50, and VGG16), five optimization algorithms (MomentumSGD, Adagrad, RMSprop, Adadelta, and Adam), and five learning rate conditions (0.01, 0.001, 0.0001, 0.00001, and 0.000001), for a total of 75 conditions to create CNN models. From these, there was no significant difference among the CNN architectures, but VGG16 was suitable under the GPU-equipped PC environment, while InceptionV3 and ResNet50 were suitable under the general-purpose PC environment. In addition, the combined use of multiple AI models created in this study improved the accuracy of estimating the coverage of red clover compared to the previously reported method, achieving a maximum absolute error of less than 5％.

In this study, we examined the effects of runway formation on pasture surface by small mammals inhabiting grasslands in the Tohoku region on soil composition and vegetation in the pasture the following spring. One hundred and sixty locations (1 m×1 m each) were established in an orchardgrass-dominant pasture, and the area percentage of runway traces and the content of moisture, nitrate nitrogen, and ammonia nitrogen of the soil surface layer at each location were measured. Plant species emerged and their coverage were measured in the central area (0.5 m x 0.5 m) of each location, and plant species diversity was evaluated using the Simpson index. In addition, the height and coverage of orchardgrass were also recorded. Based on these results, a path analysis was conducted with a hypothesis to estimate the effects of disturbance on the grassland. The results indicated that small mammal runway formation contributed to the increase in plant species diversity and orchardgrass height through an increase in inorganic nitrogen, especially nitrate nitrogen concentration.