Soil organic matter (SOM) is the main source of soil nutrients, which are essential for the growth and development of agricultural crops. Hyperspectral remote sensing is one of the most efficient ways of estimating the SOM content. Visible, near infrared, and mid-infrared reflectance spectroscopy, combined with the partial least squares regression (PLSR) method is considered to be an effective way of determining soil properties. In this study, we used 54 different spectral pretreatments to preprocess soil spectral data. These spectral pretreatments were composed of three denoising methods, six data transformations, and three dimensionality reduction methods. The three denoising methods included no denoising (ND), Savitzky–Golay denoising (SGD), and wavelet packet denoising (WPD). The six data transformations included original spectral data, R; reciprocal, 1/R; logarithmic, log(R); reciprocal logarithmic, log(1/R); first derivative, R’; and first derivative of reciprocal, (1/R)’. The three dimensionality reduction methods included no dimensionality reduction (NDR), sensitive waveband dimensionality reduction (SWDR), and principal component analysis (PCA) dimensionality reduction (PCADR). The processed spectra were then employed to construct PLSR models for predicting the SOM content. The main results were as follows—(1) the wavelet packet denoising (WPD)-R’ and WPD-(1/R)’ data showed stronger correlations with the SOM content. Furthermore, these methods could effectively limit the correlation between the adjacent bands and, thus, prevent “overfitting”. (2) Of the 54 pretreatments investigated, WPD-(1/R)’-PCADR yielded the model with the highest accuracy and stability. (3) For the same denoising method and spectral transformation data, the accuracy of the SOM content estimation model based on SWDR was higher than that of the model based on NDR. Furthermore, the accuracy in the case of PCADR was higher than that for SWDR. (4) Dimensionality reduction was effective in preventing data overfitting. (5) The quality of the spectral data could be improved and the accuracy of the SOM content estimation model could be enhanced effectively, by using some appropriate preprocessing methods (one combining WPD and PCADR in this study).

Yellow rust is a disease with a wide range that causes great damage to wheat. The traditional method of manually identifying wheat yellow rust is very inefficient. To improve this situation, this study proposed a deep-learning-based method for identifying wheat yellow rust from unmanned aerial vehicle (UAV) images. The method was based on the pyramid scene parsing network (PSPNet) semantic segmentation model to classify healthy wheat, yellow rust wheat, and bare soil in small-scale UAV images, and to investigate the spatial generalization of the model. In addition, it was proposed to use the high-accuracy classification results of traditional algorithms as weak samples for wheat yellow rust identification. The recognition accuracy of the PSPNet model in this study reached 98%. On this basis, this study used the trained semantic segmentation model to recognize another wheat field. The results showed that the method had certain generalization ability, and its accuracy reached 98%. In addition, the high-accuracy classification result of a support vector machine was used as a weak label by weak supervision, which better solved the labeling problem of large-size images, and the final recognition accuracy reached 94%. Therefore, the present study method facilitated timely control measures to reduce economic losses.

The hyperspectral image (HSI) has nearly continuous spectral information, thus, the target of interest can be accurately identified by the subtle details of spectral properties. Spectral resolution at different scales can capture different levels of spectral features: small-scale spectral bands are beneficial for extracting global details in vision transformers, while large-scale spectral bands are more effective for local features. Transformer shows advantages in global information extraction with self-attention module and even surpasses CNNs in various tasks. Some works based on the vision transformer have performed surprisingly in HSI classification. However, single-scale vision transformers are insufficient to balance the extraction of local details and redundancy on different scales. The recent work, a multi-scale vision transformer, has provided a solution with spatial patch-wise features in image classification. Inspired by this, we propose the Cross-spectral vision transformer (CSiT) with two branches to extract pixel-wise multi-scale features and further design a multi-scale spectral embedding module to enhance local details between neighboring spectral bands. Moreover, based on the cross-attention operation, a single token for each branch is recognized as a query and used to exchange information with other branches. We evaluate the classification performance of the proposed CSiT in three classic HSI datasets with extensive experiments, showing the multi-scale vision transformer architecture has a promising result for HSI classification with one-dimensional spectral bands.

Color correction and enhancement for underwater images is challenging due to attenuation and scattering. The underwater images often have low visibility and suffer from color bias. This paper presents a novel color correction method based on color filter array (CFA) and an enhancement method based on Retinex with dense pixels and adaptive linear histogram transformation for degraded color-biased underwater images. For any digital image in the RGB space, which is captured by digital camera with CFA, their RGB values are dependent and coupled because of the interpolation process. So we try to compensate red channel attenuation of underwater degraded images from the green channel and blue channel. Retinex model has been widely used to efficiently handle low brightness and blurred images. The McCann Retinex (MR) method selects a spiral path for pixel comparison to estimate illumination. However, the simple path selection doesn't include global light dark relationship of the whole image. So we design a scheme to gain much well-distributed and denser pixels to obtain more precise intensity of illumination. Besides, we design a piecewise linear function for histogram transform, which is adaptive to the whole RGB value. Experiments on a large number of underwater degraded images show that, the processed images by our method have clearer details and uniform visual effect for all channels in RGB color space and our method can also obtain good performance metrics.

Recently, Internet finance is increasingly popular. However, bad debt has become a serious threat to Internet financial companies. The fraud detection models commonly used in conventional financial companies is logistic regression. Although it is interpretable, the accuracy of the logistic regression still remains to be improved. This paper takes a large public loan dataset, e.g. Lending club, for example, to explore the potential of applying deep neural network for fraud detection. We first fill the missing values by a random forest. Then, an XGBoost algorithm is employed to select the most discriminate features. After that, we propose to use a synthetic minority oversampling technique to deal with the sample imbalance. With the preprocessed data, we design a deep neural network for Internet loan fraud detection. Extensive experiments have been conducted to demonstrate the outperformance of the deep neural network compared with the commonly-used models. Such a simple yet effective model may brighten the application of deep learning in anti-fraud for Internet loans, which would benefit the financial engineers in small and medium Internet financial companies.