Urban forests can maintain urban ecological balance and improve environmental quality, but it is difficult to identify such forests accurately due to its complex and fragmented features. This study aims to develop a deep-learning network to extract the urban forest spatial distribution from high-spatial resolution image, like from Chinese Gaofen-2 (GF-2) image. Based on the GF-2 surface reflectance image and urban forest samples known in prior, this study firstly create a U-Net network to train and generate a predictive model to identify the urban forest, and then used the trained model to get the spatial distribution of urban forest in the Beibei district. Results showed that the U-Net Network can predict urban forests distribution accurately and rapidly.

Huiyun Yang, Shujian Huang, Xin-Yu Dai, Jiajun Chen. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

In this study, we used HyMap-C airborne hyperspectral imagery and ground samples collected synchronously to explore the estimation of soil heavy metal concentration. Preprocessing methods such as first-order derivative were used to enhance the weak spectral information related heavy metals. The multivariate stepwise regression method was used to select the spectral characteristics and establish the inversion model. The samples were divided into 3 parts, model set, validation set and test set. For the arsenic (As) the errors of the samples sets were 0.55, 0.75, 0.44, and the root-mean-square error were 51.20, 30.12, 32.78 mg/kg respectively. The results show that this method can predict the heavy metals arsenic in the study area.