Rapid detection of illicit opium poppy plants using UAV (unmanned aerial vehicle) imagery has become an important means to prevent and combat crimes related to drug cultivation. However, current methods rely on time-consuming visual image interpretation. Here, the You Only Look Once version 3 (YOLOv3) network structure was used to assess the influence that different backbone networks have on the average precision and detection speed of an UAV-derived dataset of poppy imagery, with MobileNetv2 (MN) selected as the most suitable backbone network. A Spatial Pyramid Pooling (SPP) unit was introduced and Generalized Intersection over Union (GIoU) was used to calculate the coordinate loss. The resulting SPP-GIoU-YOLOv3-MN model improved the average precision by 1.62% (from 94.75% to 96.37%) without decreasing speed and achieved an average precision of 96.37%, with a detection speed of 29 FPS using an RTX 2080Ti platform. The sliding window method was used for detection in complete UAV images, which took approximately 2.2 sec/image, approximately 10× faster than visual interpretation. The proposed technique significantly improved the efficiency of poppy detection in UAV images while also maintaining a high detection accuracy. The proposed method is thus suitable for the rapid detection of illicit opium poppy cultivation in residential areas and farmland where UAVs with ordinary visible light cameras can be operated at low altitudes (relative height < 200 m).

The patterns and drivers of soil microbial communities in forest plantations remain inadequate although they have been extensively studied in natural forest and grassland ecosystems. In this study, using data from 12 subtropical plantation sites, we found that the overstory tree biomass and tree cover increased with increasing plantation age. However, there was a decline in the aboveground biomass and species richness of the understory herbs as plantation age increased. Biomass of all microbial community groups (i.e. fungi, bacteria, arbuscular mycorrhizal fungi and actinomycete) decreased with increasing plantation age; however, the biomass ratio of fungi to bacteria did not change with increasing plantation age. Variation in most microbial community groups was mainly explained by the understory herb (i.e. herb biomass and herb species richness) and overstory trees (i.e. tree biomass and tree cover), while soils (i.e. soil moisture, soil organic carbon and soil pH) explained a relative low percentage of the variation. Our results demonstrate that the understory herb layer exerts strong controls on soil microbial community in subtropical plantations. These findings suggest that maintenance of plantation health may need to consider the management of understory herb in order to increase the potential of plantation ecosystems as fast-response carbon sinks.

Opium poppies are a major source of traditional drugs, which are not only harmful to physical and mental health, but also threaten the economy and society. Monitoring poppy cultivation in key regions through remote sensing is therefore a crucial task; the location coordinates of poppy parcels represent particularly important information for their eradication by local governments. We propose a new methodology based on deep learning target detection to identify the location of poppy parcels and map their spatial distribution. We first make six training datasets with different band combinations and slide window sizes using two ZiYuan3 (ZY3) remote sensing images and separately train the single shot multibox detector (SSD) model. Then, we choose the best model and test its performance using 225 km² verification images from Lao People’s Democratic Republic (Lao PDR), which exhibits a precision of 95% for a recall of 85%. The speed of our method is 4.5 km²/s on 1080TI Graphics Processing Unit (GPU). This study is the first attempt to monitor opium poppies with the deep learning method and achieve a high recognition rate. Our method does not require manual feature extraction and provides an alternative way to rapidly obtain the exact location coordinates of opium poppy cultivation patches.

Urban industrial land (UIL), which is classified for industrial purposes, is an indispensable component of urban land. Obtaining up-to-date and timely UIL details from the industrial development perspective has practical significance for UIL planning. Therefore, we propose a practical method for integrating UIL identification and use efficiency evaluation at the parcel scale based on multi-source data. The Open Street Map (OSM) data were utilized to generate parcels, which served as basic analytical units. Point of Interest (POI) data combined with a Continuous Bag-of-Words (CBoW)-based Word2Vec model was utilized to acquire UIL information. The entropy-weight Technique for Order Preference by Similarity to Ideal Solution method, combined with economic and environmental UIL indicators obtained from remote sensing images, ground observation data, and statistical data, was used to evaluate UIL use efficiency, and the spatial distribution and utilization degree of UIL within Beijing’s fifth ring road was analyzed. The region within Beijing’s fifth ring road was classified into commercial land, industrial land, and other types, with an overall accuracy of 92.24%. With this method, we found that the distribution of UIL presented a ring structure developing outwards along the ring roads and contained concentrated commercial areas. UIL utilization exhibited a south–north differentiation, and industrial land had lower use efficiency. Our work fully utilized the available fine-scale multi-source data.