Airborne electromagnetics is an effective and efficient exploration tool in shallow mineral exploration for its high efficiency and low cost. In 2016, airborne electromagnetic and airborne magnetic surveys have been carried out at the border of Xinjiang Uygur Autonomous Region and Gansu Province, the Northwest China. With an integrated system, the airborne electromagnetics and airborne magnetic data were collected simultaneously by AreoTEM-IV system from Aeroquest International Limited in Vancouver, BC, Canada, and the CS3 Cesium Vapor magnetometer from Scintrex in Concord, ON, Canada. About 3149 line-km of both data with 250 m line space were acquired. After data processing, the comprehensive analysis and interpretation of resistivity and magnetic anomalies has been carried out to infer lithological structure and outline the potential ore deposits. Verified by the ground surveys, seven outlined anomalies are consistent with the known ore sites, and one new gold deposit and several mineralization clues were found. The prospective reserves of gold are expected to exceed 10 tons. Besides, some prospecting target areas were outlined as the possible locations of copper–nickel deposits. The successful case shows the airborne magnetic data accords with geological structures, and the airborne electromagnetic method is effective in finding metal mineral resources, which can help to quickly identify potential ore targets with no surface outcrop.

With the development of cloud computing, more and more security problems like “fuzzy boundary” are exposed. To solve such problems, unsupervised anomaly detection is increasingly used in cloud security, where density estimation is commonly used in anomaly detection clustering tasks. However, in practical use, the excessive amount of data and high dimensionality of data features can lead to difficulties in data calibration, data redundancy, and reduced effectiveness of density estimation algorithms. Although auto-encoders have made fruitful progress in data dimensionality reduction, using auto-encoders alone may still cause the model to be too generalized and unable to detect specific anomalies. In this paper, a new unsupervised anomaly detection method, MemAe-gmm-ma, is proposed. MemAe-gmm-ma generates a low-dimensional representation and reconstruction error for each input sample by a deep auto-encoder. It adds a memory module inside the auto-encoder to better learn the inner meaning of the training samples, and finally puts the low-dimensional information of the samples into a Gaussian mixture model (GMM) for density estimation. MemAe-gmm-ma demonstrates better performance on the public benchmark dataset, with a 4.47% improvement over the MemAe model standard F1 score on the NSL-KDD dataset, and a 9.77% improvement over the CAE-GMM model standard F1 score on the CIC-IDS-2017 dataset.

In this Letter, we propose an all-optical diffractive deep neural network modeling method based on nonlinear optical materials. First, the nonlinear optical properties of graphene and zinc selenide (ZnSe) are analyzed. Then the optical limiting effect function corresponding to the saturation absorption coefficient of the nonlinear optical materials is fitted. The optical limiting effect function is taken as the nonlinear activation function of the neural network. Finally, the all-optical diffractive neural network model based on nonlinear materials is established. The numerical simulation results show that the model can effectively improve the nonlinear representation ability of the all-optical diffractive neural network. It provides a theoretical support for the further realization of a photonic artificial intelligence chip based on nonlinear optical materials.

An airborne transient electromagnetic (TEM) has been conducted in Baiyangdian Area to map resistivity distribution within the alluvial and lacustrine aquifers. This investigation evaluated the reliability of resistivity models of the TEM data to infer lithological distribution in alluvial and lacustrine aquifers. The collected airborne TEM data were processed and inverted using spatially constrained 1D inversion method. And the 3D electrical structure, which maps electrical resistivity trends to depths of about 160 m, can be established through interpolation. Comparison of the resistivity models to drill logs indicates resistive permeable coarse-grained sediments and conductive fine-grained sediments which are relatively impermeable. Hence, the 3D electrical structure that are related to lateral and vertical variation in lithology, can serve as baseline information for groundwater potential identification. This research indicates that groundwater detection is an ideal target for mapping with airborne TEM techniques because of the high electrical resistivity of permeable coarse-grained deposits and its contrast with impermeable fine-grained deposits.

No abstract