Abstract: A stability control method and device based on particle active disturbance rejection are provided. The method includes: establishing an active disturbance rejection controller model based on a dynamic model and a speed loop control model of a tethered balloon system, where the speed loop control model is established through theoretical modeling of executive components of a control system of the tethered balloon system; and optimizing to-be-optimized parameters of the active disturbance rejection controller model using a particle swarm optimization algorithm, determining an optimal active disturbance rejection controller model, and using the optimal active disturbance rejection controller model to implement stability control of a photoelectric pod. An active disturbance rejection controller is optimized by using a particle swarm optimization algorithm, which can effectively isolate the internal and external disturbances of the photoelectric pod and improve the imaging stability of the photoelectric pod.

Abstract: The present disclosure discloses an extraction method of raft culture area based on multi-temporal optical remote sensing images, including: constructing a raft culture marker sample library including culture types such as fish, shellfish, and algae; optimizing the deep learning model of the UNet network by using ASPP (Atrous Spatial Pyramid Pooling) and the shape constraint module; using the deep learning model to extract a corresponding multi-temporal raft culture area by using the multi-temporal optical remote sensing images with medium resolution in the target area; combining prior knowledge, fusing the extraction results of the raft culture area to obtain a final extraction results of the raft culture area.

Abstract: This invention discloses a practical method for landslide detection in large space, which comprises the following steps: image synthesis, ice and snow detection, removal of non-potential landslide area, detection of potential landslide area, feature calculation, landslide detection model construction and precision validation; this invention avoids radiometric correction and outlier by detecting landslide from synthetic image. That guarantees practical applicability of the proposal. Firstly, detecting potential landslides can avoid the imbalanced sample distribution issue between background objects and landslides when training the landslide detection model. The landslide is further detected by building a random forest model based on the spectral features and textural features of potential landslide pixels in different neighboring time domains. It fully considers the changes of objects in different time domains, and lays a foundation for efficient landslide extraction.

Abstract: A magnetic compensation method based on an aeromagnetic compensation error model includes: acquiring an upper limit of an error of a magnetic noise caused by both an environmental background field in an exploration area and an aeromagnetic flight platform, by using the aeromagnetic compensation error model, before an actual flight; determining, according to the upper limit, whether the environmental background field and the aeromagnetic flight platform are suitable for the actual flight, and if so, performing a calibration flight to acquire a compensation coefficient; and acquiring data of an attitude term by performing the actual flight, calculating an interference magnetic field by the data of the attitude term and the compensation coefficient, and performing magnetic compensation.

Abstract: A method for extracting an oil storage tank based on a high-spatial-resolution remote sensing image is provided, including: acquiring an oil storage tank sample, and randomly dividing the oil storage tank sample into a training set and a testing set; building an oil storage tank extraction model based on a Res2-Unet model structure, wherein the Res2-Unet is a deep learning network based on a UNet semantic segmentation structure, and a Res2Net convolution block is configured to change a feature interlayer learning to a granular learning and is arranged in a residual mode; and performing a precision verification on the testing set.

Abstract: A method for soil moisture retrieval using multi-channel collaboration algorithm and passive microwave radiometry including: establishing mathematical relationship formula between brightness temperatures at any two channels according to microwave radiative transfer equation; collecting actual brightness temperatures of core channel and collaborative channels; selecting parameters to be retrieved including soil moisture value; giving a series of estimated values of parameters to be retrieved, calculating a series of predicted brightness temperatures of collaborative channels according to actual brightness temperature of core channel, microwave radiative transfer equation and mathematical relationship formula, comparing predicted brightness temperatures with actual brightness temperature, and determining soil moisture value.

Abstract: A system for numerical simulation and test verification of icing characteristics of an aerostat includes an aerostat icing characteristic calculation model and an aerostat icing characteristic test system. The aerostat icing characteristic calculation model is configured to obtain icing data of the aerostat through numerical simulation, and the aerostat icing characteristic test system is configured to obtain icing characteristic data of the aerostat through a physical simulation test. The calculation result obtained through the numerical simulation and the test result obtained through the physical simulation test are mutually verified and improved, so as to facilitate the in-depth research and accurate analysis of the icing characteristics of the aerostat.

Abstract: A system for numerical simulation and test verification of icing characteristics of an aerostat includes an aerostat icing characteristic calculation model and an aerostat icing characteristic test system. The aerostat icing characteristic calculation model is configured to obtain icing data of the aerostat through numerical simulation, and the aerostat icing characteristic test system is configured to obtain icing characteristic data of the aerostat through a physical simulation test. The calculation result obtained through the numerical simulation and the test result obtained through the physical simulation test are mutually verified and improved, so as to facilitate the in-depth research and accurate analysis of the icing characteristics of the aerostat.