No abstract

No abstract

Drought stress seriously affects crop growth, development, and grain production. Existing machine learning methods have achieved great progress in drought stress detection and diagnosis. However, such methods are based on a hand-crafted feature extraction process, and the accuracy has much room to improve. In this paper, we propose the use of a deep convolutional neural network (DCNN) to identify and classify maize drought stress. Field drought stress experiments were conducted in 2014. The experiment was divided into three treatments: optimum moisture, light drought, and moderate drought stress. Maize images were obtained every two hours throughout the whole day by digital cameras. In order to compare the accuracy of DCNN, a comparative experiment was conducted using traditional machine learning on the same dataset. The experimental results demonstrated an impressive performance of the proposed method. For the total dataset, the accuracy of the identification and classification of drought stress was 98.14% and 95.95%, respectively. High accuracy was also achieved on the sub-datasets of the seedling and jointing stages. The identification and classification accuracy levels of the color images were higher than those of the gray images. Furthermore, the comparison experiments on the same dataset demonstrated that DCNN achieved a better performance than the traditional machine learning method (Gradient Boosting Decision Tree GBDT). Overall, our proposed deep learning-based approach is a very promising method for field maize drought identification and classification based on digital images.

No abstract

No abstract

A paleomagnetic study of late Paleozoic rocks in two areas of northwestern China helps to constrain the timing of collision between Tarim and the Junggar part of Eurasia along Tianshan. A primary Late Permian direction (D/I = 198/−59, K=24, A95=12.6) is derived from seven sites (53 samples) from the Heavenly Lake (Tianzhi) section in northern Tianshan that has both normal and reversed polarities and passes a fold test at the 99% confidence level. This result gives a latitude of 39°N in the Late Permian for southern Junggar. Twenty‐two sites (144 samples) from the Devonian and Carboniferous rocks across Tianshan reveal postfolding remagnetizations some of which are interpreted as being acquired in the Permian due to the Tarim‐Eurasia collision. The Late Permian paleomagnetic pole from the Heavenly Lake section is statistically indistinguishable from three published Late Permian poles from Tarim indicating closure of the Tianshan ocean and suturing of Tarim and Junggar before that time. These paleomagnetic poles from northwestern China are, however, significantly different from those of stable Eurasia, suggesting substantial later relative motion that can be partly accounted for by the progressive closure of the Mongolo‐Okhotsk ocean and associated tectonic rotations. The absence of a discernable Permian ocean record west of the Khangay highland in central Mongolia requires that the rotations be accommodated within a diffusive plate boundary in the Eurasian continent. A Late Permian continental plate reconstruction is presented that takes into consideration these new paleomagnetic results and other geological constraints.

Soil moisture is one of the most important indicators for agricultural drought monitoring. In this paper we present a comprehensive review to the progress in remote sensing of soil moisture, with focus on discussion of the method details and problems existing in soil moisture estimation from remote sensing data. Thermal inertia and crop water stress index (CWSI) can be used for soil moisture estimation under bare soil and vegetable environments respectively. Anomaly vegetation index (AVI) and vegetation condition index (VCI) are another alternative methods for soil moisture estimation with Normalized difference vegetation index (NDVI). Both NDVI and land surface temperature (LST) are considered in temperature vegetation index (TVI), vegetation supply water index (VSWI) and vegetation temperature condition index (VTCI). Microwave remote sensing is the most effective technique for soil moisture estimation. Active microwave can provide high spatial resolution but is sensitive to soil rough and vegetation. Passive microwave has a low resolution and revisit frequency but it has more potential for large scale agricultural drought monitoring. Integration of optical/ IR and microwave remote sensing may be the practical method for drought monitoring in both accuracy and in efficiency.

No abstract