Soil Bacterial Community in the Multiple Cropping System Increased Grain Yield Within 40 Cultivation Years

The shortage of land resources restricts the sustainable development of agricultural production. Multiple cropping has been widely used in Southern China, but whether the continuous planting will cause a decline in soil quality and crop yield is unclear. To test whether multiple cropping could increase grain yield, we investigated the farmlands with different cultivation years (10–20 years, 20–40 years, and >40 years). Results showed that tobacco-rice multiple cropping rotation significantly increased soil pH, nitrogen nutrient content, and grain yield, and it increased the richness of the bacterial community. The farmland with 20–40 years of cultivation has the highest soil organic carbon (SOC), ammonium nitrogen, and grain yield, but there is no significant difference in the diversity and structure of the bacterial community in farmlands with different cultivation years. The molecular ecological network indicated that the stability of the bacterial community decreased across the cultivation years, which may result in a decline of farmland yields in multiple cropping system> 40 years. The Acidobacteria members as the keystone taxa (Zi ≥ 2.5 or Pi ≥ 0.62) appeared in the tobacco-rice multiple cropping rotation farmlands, and the highest abundance of Acidobacteria was found in the farmland with the highest SOC and ammonium nitrogen content, suggesting Acidobacteria Gp4, GP7, GP12, and GP17 are important taxa involved in the soil carbon and nitrogen cycle. Therefore, in this study, the multiple cropping systems for 20 years will not reduce the crop production potential, but they cannot last for more than 40 years. This study provides insights for ensuring soil quality and enhancing sustainable agricultural production capacity.

Hyperparameter Optimization and Regularization on Fashion-MNIST Classification

Nowadays the most exciting technology breakthrough has been the rise of the deep learning. In computer vision Convolutional Neural Networks (CNN or ConvNet) are the default deep learning model used for image classification problems. In these deep network models, feature extraction is figure out by itself and these models tend to perform well with huge amount of samples. Herein we explore the impact of various Hyper-Parameter Optimization (HPO) methods and regularization techniques with deep neural networks on FashionMNIST (F-MNIST) dataset which is proposed by Zalando Research. We have proposed deep ConvNet architectures with Data Augmentation and explore the impact of this by configuring the hyperparameters and regularization methods. As deep learning requires a lots of data, the insufficiency of image samples can be expand through various data augmentation methods like Cropping, Rotation, Flipping, and Shifting. The experimental results show impressive results on this new benchmarking dataset F-MNIST

IDENTIFIKASI DAN TINGKAT KERUSAKAN OLEH SERANGGAPERUSAK PADA BIBIT SENGON (Falcataria moluccana) DI PERSEMAIAN PERMANEN BALAI PENGELOLAAN DAERAH ALIRAN SUNGAI DAN HUTAN LINDUNG KAPUAS PONTIANAK

Sengon is a fast growing tree species that can be harvested in a relatively short time, with a cropping rotation of around 5-8 years. This type is chosen as one of plant type industrial forest plantation in Indonesia, because it is able to adapt various types of soil. Sengon is a tree that is an alternative that can be cultivated extensively for rehabilitation purposes of marginal lands. Suplay of quality sengon seedlings is still constrained because there are destructive insect attacks.This study aims of was to identify insects that attack sengon seedlings and determine the level of damage caused by insects at permanent nursery areas BPDASHL Kapuas Pontianak. The method used in this study is a survey method with direct observation of sengon seedlings in the nursery area.The results of the study found 8 types of destructive insect that attacks sengon seedlings (Falcataria moluccana) in the nursery area namely Eurema sp., Pteroma sp., Clania sp., Amatissa sp., Atractomorpha sp., Ferissia virgata, Valanga sp., and Conochepalus sp. The dominant insects species that attacks sengon seedlings in permanent nurseries are insects from the order Lepidoptera and non-dominant insects from order Orthoptera and Homoptera. The results showed that average percentage of destructive insect attacks is 23,33% and the average percentage the level of damage is 10% including is the low in the damage category.Keywords: destructive insects, identification, level of damage, permanent nursery, sengon seedlings

Robust Video Watermarking Scheme Based on Intra-Coding Process in MPEG-2 Style

The proposed scheme implemented a semi blind digital watermarking method for video exploiting MPEG-2 standard. The watermark is inserted into selected high frequency coefficients of plain types of discrete cosine transform blocks instead of edge and texture blocks during intra coding process. The selection is essential because the error in such type of blocks is less sensitive to human eyes as compared to other categories of blocks. Therefore, the perceptibility of watermarked video does not degraded sharply. Visual quality is also maintained as motion vectors used for generating the motion compensated images are untouched during the entire watermarking process. Experimental results revealed that the scheme is not only robust to re-compression attack, spatial synchronization attacks like cropping, rotation but also strong to temporal synchronization attacks like frame inserting, deleting, swapping and averaging. The superiority of the anticipated method is obtaining the best sturdiness results contrast to the recently delivered schemes.