Search for: All records

Interspecific hybridization is a common and effective strategy for producing disease resilient citrus cultivars, including those with tolerance to Huanglongbing (HLB) disease. Several HLB-tolerant cultivars have been developed through hybridization of mandarins (Citrus reticulata) with their wild relativePoncirus trifoliata. One such cultivar, ‘US-897’, exhibits robust tolerance to the bacteria causing HLB disease,Candidatus Liberibacter asiaticus(CLas). To explore the genetic architecture of the early transcriptional response toCandidatusLiberibacter asiaticus (CLas) infection in ‘US-897’, we performed transcriptomic analysis of the hybrid and its parents, ‘Cleopatra’ (C. reticulata) and ‘Flying Dragon’ (P. trifoliata). A haplotype-resolved genome for ‘US-897’ was generated using PacBio HiFi sequencing reads to support quantification of the expression of both theCitrus and Poncirusalleles. By profiling gene expression in this parent-offspring trio, we were able to determine the mode of inheritance for genes differentially expressed between parents (‘Cleopatra’ and ‘Flying Dragon’) and their interspecific hybrid (‘US-897’), with the majority genes exhibiting non-additive patterns of gene expression inheritance. Additionally, analysis of allele-specific expression in the hybrid ‘US-897’ revealed the contribution of cis- versus trans-acting regulatory variants on genes with additive and non-additive modes of inheritance. A strong correlation between differential expression between parents and allele-specific expression in ‘US-897’ suggests that cis-regulatory variation is a significant source of expression divergence between species. Finally, genes responsive to infection withCLas were identified to explore how gene regulation associated with tolerance to HLB was rewired betweenCitrusand its relativePoncirus. 

Accurate identification of inundated areas is crucial for mitigating the impacts of flooding, which causes numerous casualties and significant economic losses. While polarimetric synthetic aperture radar (PolSAR) data have been utilized to detect inundated regions, the information contained within PolSAR features remains severely underutilized. We introduce a novel approach that involves extracting a large number of PolSAR features through various PolSAR decomposition techniques, selecting the most important ones using the decision tree–recursive feature elimination (DT-RFE) method, and ultimately detecting inundation using a convolutional neural network (CNN) model. The hybrid DT-RFE–CNN model was trained and tested over a region in southeastern North Carolina during Hurricane Florence on September 18, 2018, using PolSAR features derived from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). In terms of flood-mapping efficacy, the DT-RFE–CNN model outperformed a CNN model that used only PolSAR data across all metrics in both the training and testing stages. The performance of the trained DT-RFE–CNN model was evaluated by testing it over the same region for four more days (September 19, 20, 22, and 23, 2018); it achieved an average accuracy, precision, recall, F1 score, and intersection-over-union of 0.9304, 0.9089, 0.9584, 0.9324, and 0.8738, respectively, outperforming both the classical Otsu method and the FT-Transformer model using features selected by DT-RFE. Finally, we assessed the model’s generalizability by mapping another significant flood event, caused by Hurricane Harvey in Texas between August and September 2017. Based on the results, the hybrid model can accurately detect flooding, even in regions on which it has not been trained. Thus, the proposed method can facilitate flood monitoring and response efforts. 

Moisture plays a key role in the energetics of hurricanes. Using a convolutional autoencoder, a state-of-the-art deep learning approach to spatial pattern classification, with k-means we identified four representative clusters of total column water vapor (TCWV) patterns around North Atlantic hurricanes. These four clusters exhibit distinct spatial distributions of TCWV in terms of amount, symmetry, and areal extent. Cluster 1 has a compact, symmetric, and moderate moisture pattern which we refer to as medium moisture symmetrical. Cluster 2 is high moisture symmetrical as these hurricanes have an abundance of moisture with a widespread and symmetric pattern. Cluster 3 is low moisture asymmetrical as it represents the driest conditions especially in the northwest. Cluster 4 has high moisture near the center but exhibits a pattern with the strongest contrast between dryness in the northwest and wetness in the southeast, thus we label it high moisture asymmetrical. Each cluster has distinct geographical and temporal distributions, indicating differences in dynamic and thermodynamic environmental conditions associated with each cluster's moisture pattern. Additionally, hurricane intensity, size, and precipitation features vary among the four clusters, characteristics which are closely associated with the moisture and environmental conditions of each cluster. Our study's application of a deep learning method in classifying spatial patterns of moisture around hurricanes highlights the importance of moisture conditions in a hurricane's evolution. 

Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying financial LLMs (FinLLMs) locally are crucial for institutions and individuals. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank structure and quantization technique to significantly reduce computational requirements while maintaining model performance. We also employ data and pipeline parallelism to enable local finetuning on commodity GPUs. Experiments on financial datasets validate the efficacy of our approach in yielding notable improvements over the base models.