Search

The accurate prediction of gas well production is one of the key factors affecting the economical and efficient development of tight gas wells. The traditional oil and gas well production prediction method assumes strict conditions and has a low prediction accuracy in actual field applications. At present, intelligent algorithms based on big data have been applied in oil and gas well production prediction, but there are still some limitations. Only learning from data leads to the poor generalization ability and anti-interference ability of prediction models. To solve this problem, a production prediction method of tight gas wells based on the decline curve and data-driven neural network is established in this paper. Based on the actual production data of fractured horizontal wells in three tight gas reservoirs in the Ordos Basin, the prediction effect of the Arps decline curve model, the SPED decline curve model, the MFF decline curve model, and the combination of the decline curve and data-driven neural network model is compared and analyzed. The results of the case analysis show that the MFF model and the combined data-driven model have the highest accuracy, the average absolute percentage error is 14.11%, and the root-mean-square error is 1.491, which provides a new method for the production prediction of tight gas wells in the Ordos Basin. [ABSTRACT FROM AUTHOR]

The production of tight gas wells decreases rapidly, and the traditional method is difficult to accurately predict the production of tight gas wells. At present, intelligent algorithms based on big data have been applied in oil and gas well production prediction, but there are still some technical problems. For example, the traditional error back propagation neural network (BP) still has the problem of finding the local optimal value, resulting in low prediction accuracy. In order to solve this problem, this paper establishes the output prediction method of BP neural network optimized with the sparrow search algorithm (SSA), and optimizes the hyperparameters of BP network such as activation function, training function, hidden layer, and node number based on examples, and constructs a high-precision SSA-BP neural network model. Data from 20 tight gas wells, the SSA-BP neural network model, Hongyuan model, and Arps model are predicted and compared. The results indicate that when the proportion of the predicted data is 20%, the SSA-BP model predicts an average absolute mean percentage error of 20.16%. When the proportion of forecast data is 10% of the total data, the SSA-BP algorithm has high accuracy and high stability. When the proportion of predicted data is 10%, the mean absolute average percentage error is 3.97%, which provides a new method for tight gas well productivity prediction. [ABSTRACT FROM AUTHOR]

Summary: MiRNAs have been reported to be the key regulators involving a wide range of biological processes in diverse plant species, but their functions in switchgrass, an important biofuel and forage crop, are largely unknown. Here, we reported the novel function of miR528, which has expanded to four copies in switchgrass, in controlling biomass trait of tillering number and regrowth rate after mowing. Blocking miR528 activity by expressing short tandem target mimic (STTM) increased tiller number and regrowth rate after mowing. The quadruple pvmir528 mutant lines derived from genome editing also showed such improved traits. Degradome and RNA‐seq analysis, combined with in situ hybridization assay revealed that up‐regulation of two miR528 targets coding for Cu/Zn‐SOD enzymes, might be responsible for the improved traits of tillering and regrowth in pvmir528 mutant. Additionally, natural variations in the miR528‐SOD interaction exist in C3 and C4 monocot species, implying the distinct regulatory strength of the miR528‐SOD module during monocot evolution. Overall, our data illuminated a novel role of miR528 in controlling biomass traits and provided a new target for genetic manipulation‐mediated crop improvement. [ABSTRACT FROM AUTHOR]

The lack of genome editing platforms has hampered efforts to study and improve forage crops that can be grown on lands not suited to other crops. Here, we established efficient Agrobacterium‐mediated clustered regularly interspaced palindromic repeats (CRISPR)/CRISPR‐associated nuclease 9 (Cas9) genome editing in a perennial, stress‐tolerant forage grass, sheepgrass (Leymus chinensis). By screening for active single‐guide RNAs (sgRNAs), accessions that regenerate well, suitable Agrobacterium strains, and optimal culture media, and co‐expressing the morphogenic factor TaWOX5, we achieved 11% transformation and 5.83% editing efficiency in sheepgrass. Knocking out Teosinte Branched1 (TB1) significantly increased tiller number and biomass. This study opens avenues for studying gene function and breeding in sheepgrass. [ABSTRACT FROM AUTHOR]

In cases where a client suffers from completely unlabeled data, unsupervised learning has difficulty achieving an accurate fault diagnosis. Semi-supervised federated learning with the ability for interaction between a labeled client and an unlabeled client has been developed to overcome this difficulty. However, the existing semi-supervised federated learning methods may lead to a negative transfer problem since they fail to filter out unreliable model information from the unlabeled client. Therefore, in this study, a dynamic semi-supervised federated learning fault diagnosis method with an attention mechanism (SSFL-ATT) is proposed to prevent the federation model from experiencing negative transfer. A federation strategy driven by an attention mechanism was designed to filter out the unreliable information hidden in the local model. SSFL-ATT can ensure the federation model's performance as well as render the unlabeled client capable of fault classification. In cases where there is an unlabeled client, compared to the existing semi-supervised federated learning methods, SSFL-ATT can achieve increments of 9.06% and 12.53% in fault diagnosis accuracy when datasets provided by Case Western Reserve University and Shanghai Maritime University, respectively, are used for verification. [ABSTRACT FROM AUTHOR]

The efficiency of deep learning-based fault diagnosis methods for bearings is affected by the sample size of the labeled data, which might be insufficient in the engineering field. Self-training is a commonly used semi-supervised method, which is usually limited by the accuracy of features for unlabeled data screening. It is significant to design an efficient training mechanism to extract accurate features and a novel feature fusion mechanism to ensure that the fused feature is capable of screening. A novel training mechanism of multi-scale recursion (MRAE) is designed for Autoencoder in this article, which can be used for accurate feature extraction with a small amount of labeled data. An attention gate-based fusion mechanism was constructed to make full use of all useful features in the sense that it can incorporate distinguishing features on different scales. Utilizing large numbers of unlabeled data, the proposed multi-scale recursive semi-supervised deep learning fault diagnosis method with attention gate (MRAE-AG) can efficiently improve the fault diagnosis performance of DNNs trained by a small number of labeled data. A benchmark dataset from the Case Western Reserve University bearing data center was used to validate this novel method which shows that 7.76% accuracy improvement can be achieved in the case when only 10 labeled samples was available for supervised training of the DNN-based fault diagnosis model. [ABSTRACT FROM AUTHOR]

SUMMARY: In rice (Oryza sativa), the lemma and palea protect the internal organs of the floret，provide nutrients for seed development, and determine grain size. We previously revealed that a trans‐acting small interfering RNA targeting AUXIN RESPONSE FACTORS (tasiR‐ARF) regulates lemma polarity establishment via post‐transcriptional repression of AUXIN RESPONSE FACTORS (ARFs) in rice. TasiR‐ARF formation requires RNA‐DEPENDENT RNA POLYMERASE 6 (RDR6). However, the underlying molecular mechanism of the tasiR‐ARF–ARF regulon in lemma development remains unclear. Here, by genetic screening for suppressors of the thermosensitive mutant osrdr6‐1, we identified three suppressors, huifu 1 (hf1), hf9, and hf17. Mapping‐by‐sequencing revealed that HF1 encodes a MYB transcription factor belonging to the KANADI1 family. The hf1 mutation partially rescued the osrdr6‐1 lemma defect but not the defect in tasiR‐ARF levels. DNA affinity purification sequencing analysis identified 17 725 OsKANADI1‐associated sites, most of which contain the SPBP‐box binding motif (RGAATAWW) and are located in the promoter, protein‐coding, intron, and intergenic regions. Moreover, we found that OsKANADI1 could directly bind to the intron of OsARF3a in vitro and in vivo and promote OsARF3a expression at the transcriptional level. In addition, hf9 and hf17 are intragenic suppressors containing mutations in OsRDR6 that partially rescue tasiR‐ARF levels by restoring OsRDR6 protein levels. Collectively, our results demonstrate that OsKANADI1 and tasiR‐ARFs synergistically maintain the proper expression of OsARF3a and thus contribute to rice lemma development. Significance Statement: The lemma and palea are unique and important organs for rice, providing nutrients and protection for floret and seed development, and directly affecting grain size. Our findings show that the expression of OsARF3a was controlled by both OsKANADI1 and via RDR6 at the transcription and post‐transcription levels, thus ensuring the normal development of glumes in rice. [ABSTRACT FROM AUTHOR]

Leymus chinensis , a dominant perennial grass in the Eurasian Steppe, is well known for its remarkable adaptability and forage quality. Hardly any breeding has been done on the grass, limiting its potential in ecological restoration and forage productivity. To enable genetic improvement of the untapped, important species, we obtained a 7.85-Gb high-quality genome of L. chinensis with a particularly long contig N50 (318.49 Mb). Its allotetraploid genome is estimated to originate 5.29 million years ago (MYA) from a cross between the Ns-subgenome relating to Psathyrostachys and the unknown Xm-subgenome. Multiple bursts of transposons during 0.433-1.842 MYA after genome allopolyploidization, which involved predominantly the Tekay and Angela of LTR retrotransposons, contributed to its genome expansion and complexity. With the genome resource available, we successfully developed a genetic transformation system as well as the gene-editing pipeline in L. chinensis . We knocked out the monocot-specific miR528 using CRISPR/Cas9, resulting in the improvement of yield-related traits with increases in the tiller number and growth rate. Our research provides valuable genomic resources for Triticeae evolutionary studies and presents a conceptual framework illustrating the utilization of genomic information and genome editing to accelerate the improvement of wild L. chinensis with features such as polyploidization and self-incompatibility.