The ecological function of cultivated land is ever declining globally. Non-cultivated habitat is the key factor to enhance the cultivated land and ecosystem services. It is very important to accurately identify its types and boundaries. However, it is still lacking in high-quality labelled datasets for the habitat types in complex agricultural landscapes. Conventional remote sensing is often required to accurately extract the micro-scale terrain transition zone. Remote sensing data resolution has been limited to low classification accuracy. Existing deep learning models can improve the performance of the semantic segmentation. Some problems still remain, such as the incomplete parcel boundaries, fuzzy edges, and slender feature fractures. The edge perception module is applied to the extraction of the cultivated land blocks and ridges, which significantly improved the recognition accuracy. In this study, a high-resolution image dataset of remote sensing was constructed for the habitat of the cultivated land. The edge perception, DeeplabV3+ model, was created to realize accurate recognition of the habitat types of the cultivated land system at a low computational cost. Firstly, the Pegasus V500 vertical takeoff and landing fixed-wing UAV was used to collect the ultra-high resolution remote sensing images. Rasterio was used to cut them after UAV assembly. A combination of the SAM-Labelme automatic labeling and manual correction was utilized to generate the VOC dataset labels from the trimmed images in the study area. The label classification was referred to the classification of non-cultivated habitats by the European QuESSA project. 15 types of habitat types were constructed for the cultivated land, according to the cultivated land and no cultivated habitat in Hailun, one of the key areas of the black soil in Northeast China; The edge perception, DeeplabV3+ network, was constructed and then optimized, And then the VOC dataset tag was used to train the model, and finally the model was obtained to identify the habitat types of cultivated land. The improved network adopted the DeepLabV3+ network as the benchmark model. A hierarchical deformable convolution was employed in the encoder, where high accuracy was obtained with the reduction of 88.85% of training parameters. The decoder was also integrated with the multi-scale features and dual-modal edge perception, in order to achieve the fusion of the semantic features. A channel attention mechanism was added to the low-level features in order to enhance the key information and suppress noise. A Mixed Loss function and Layering Differential Learning rate were gradually integrated after optimization. The experimental results show that the edge perception DeepLabV3+ model, included a VOC dataset of 15 types of farmland habitats. The proposed model achieves an average Intersection over Union (IoU) of 66.55% and an accuracy of 80.31%, which represent respective improvements of 9.74% and 4.05% in comparison to the baseline network (DeepLabV3+). Ablation experiments verified that the explicit and implicit modalities of the edge perception module enhanced the IoU of micro-linear habitats, such as the field ridges and production roads by 6.99%-36.56%. The visualization data indicate that the edge perception, DeepLabV3+ model increased the minimum effective resolution unit from 10-30 m to 1-3 m. Compared with the baseline model, the improved model required only a 5.5% increase in training time, yet its mean Intersection over Union (IoU) was improved by 9.74%. This finding can provide an edge in perception semantic segmentation for habitat identification in farmland. Meter-level precision was also achieved in the habitat identification at a lower cost. The finding can also provide a technical basis to interpret the habitats of the micro-scale farmland.

Iron tailings and wastes have been generated by a large number of iron ore mines in the semi-arid ecologically fragile areas of western Liaoning Province in China. The resulting environmental pollution and the scarcity of soil sources can also pose a serious threat to the reclamation of abandoned mine sites, such as open pits. In this study, the large-scale agricultural resource utilization of iron tailings was proposed to construct a reclaimed farmland soil profile in the western Liaoning Province, China. Specifically, the iron tailings and wastes were also used to fill the mining pits. The iron tailings and normal farmland soils were collected from the same region. A series of experiments were then carried out on the basic physico-chemical properties, elemental content, and utilization feasibility of iron tailings. According to the theories of “the niche of soil layer” and “the critical layer of the soil”, the function of iron tailings was explored as the soil profile material. The technical mode was constructed for a highly arable farmland soil profile with the structure of “loamy-sandy-clayey” suitable for the semi-arid climate characteristics in the study area. The results showed that: 1) The sand grain content of iron tailings ranged from 28.49 % to 33.23%, while the silt content was 66.11% to 71.64%, and the clay content was less than 1.0%. The pH of iron tailings was represented by the weakly alkaline. At the same time, the conductivity was fully meet the requirements of crop growth. The heavy metal content was much lower than the national standard of Soil environmental quality Risk control standard for soil contamination of agricultural land (GB 15618 -2018). It was also rich in the beneficial trace elements required by crops. Consequently, the iron tailings served as the reconstruction materials of the soil profile. 2) Iron tailings were utilized as the sandy structure with large intergranular pores for water storage. A soil moisture retention layer was constructed to form a soil profile configuration system from the top to the bottom of "loamy (topsoil layer)-sandy (moisture retention layer)-clay (water barrier layer)". As such, the iron tailings were used to store and preserve the water and moisture for crop growth in the semi-arid areas. Meanwhile, the iron tailings were mixed in 25% amounts into the clayey topsoil, in order to increase the thickness of the tillage layer with the better soil texture. 3) The specific construction was to make full use of the waste rock, iron tailings, subsoil red clay, and stripped topsoil produced by iron ore mining. A ‘loamy-sandy-clayey’ soil profile configuration was obtained with the “large rocks with a grain size of 20-50cm (filled up to 1m from the surface) - crushed rocks with a grain size of 4-6cm (20-30cm) - red clay (20-30cm) - iron tailings (20-30cm) - stripped topsoil (20-30cm, mixed with iron tailings of about 25%)”, in the order from the bottom to the top. Four reclamation cases were selected in Jianping County, Liaoning Province, China. Therefore, the area of cultivated land increased to solve the ecological problems caused by solid waste accumulation in mining areas. The quality of farmland was also improved to increase the yield of maize by 705 kg/hm². National food security was maintained to alleviate the contradiction between mining and agricultural land. The ecological restoration mode can be applied to similar iron ore mining areas, according to the regional conditions.