RESUMO
The microphenotype plays a key role in bridging the gap between the genotype and the complex macro phenotype. In this article, we review the advances in data acquisition and the intelligent analysis of plant microphenotyping and present applications of microphenotyping in plant science over the past two decades. We then point out several challenges in this field and suggest that cross-scale image acquisition strategies, powerful artificial intelligence algorithms, advanced genetic analysis, and computational phenotyping need to be established and performed to better understand interactions among genotype, environment, and management. Microphenotyping has entered the era of Microphenotyping 3.0 and will largely advance functional genomics and plant science.
Assuntos
Inteligência Artificial , Genômica , Fenótipo , Genômica/métodos , Genótipo , Plantas/genéticaRESUMO
The Baise horse, an indigenous horse breed mainly distributed in the Baise region of Guangxi province in southwest China, has a long history as draft animal. However, there is a lack of research regarding the origin and ancestral composition of the Baise horse. In this study, whole-genome resequencing data from 236 horses of seven Chinese indigenous horse breeds, five foreign horse breeds, and four Przewalski's horses were used to investigate the relationships between the Baise horse and other horse breeds. The results showed that foreign horse breeds had no significant impact on the formation of the Baise horse. The two southwestern horse populations, the Debao pony and the Jinjiang horse, exhibit the closest genetic affinity with the Baise horse. This is consistent with their adjacent geographical distribution. Analysis of the migration route revealed a gene flow from the Chakouyi horse into the Baise horse. In summary, our results confirm that the formation of the Baise horse did not involve participation from foreign breeds. Geographical distance emerges as a crucial factor in determining the genetic relationships with the Baise horse. Gene flows of indigenous horse breeds along ancient routes of trade activities had played a role in the formation of the Baise horse.
Assuntos
Sequenciamento Completo do Genoma , Animais , Cavalos/genética , Sequenciamento Completo do Genoma/veterinária , China , Cruzamento , Fluxo Gênico , GenomaRESUMO
In this paper, we review, compare, and analyze previous studies on agricultural machinery automatic navigation and path planning technologies. First, the paper introduces the fundamental components of agricultural machinery autonomous driving, including automatic navigation, path planning, control systems, and communication modules. Generally, the methods for automatic navigation technology can be divided into three categories: Global Navigation Satellite System (GNSS), Machine Vision, and Laser Radar. The structures, advantages, and disadvantages of different methods and the technical difficulties of current research are summarized and compared. At present, the more successful way is to use GNSS combined with machine vision to provide guarantee for agricultural machinery to avoid obstacles and generate the optimal path. Then the path planning methods are described, including four path planning algorithms based on graph search, sampling, optimization, and learning. This paper proposes 22 available algorithms according to different application scenarios and summarizes the challenges and difficulties that have not been completely solved in the current research. Finally, some suggestions on the difficulties arising in these studies are proposed for further research.
RESUMO
The ability of fluorescence hyperspectral imaging to predict heavy metal lead (Pb) concentration in oilseed rape leaves was studied in silicon-free and silicon environments. Further, the transfer stacked convolution auto-encoder (T-SCAE) algorithm was proposed based on the stacked convolution auto-encoder (SCAE) algorithm. Fluorescence hyperspectral images of oilseed rape leaves under different Pb stress contents were obtained in the silicon-free and silicon environments. The entire region of oilseed rape leaves was chosen as the region of interest (ROI) to obtain fluorescence spectra. First of all, standard normalized variable (SNV) algorithm was implemented as the preferred preprocessing method, and the fluorescence spectral data processed by SNV was utilized for further analysis. Further, SCAE was used to reduce the dimensionality of the best pre-processed spectral data, and compared with the traditional dimensionality reduction algorithm. Finally, the optimal SCAE deep learning network was transferred to obtain the T-SCAE model to verify the transferability between the deep learning models in silicon-free and silicon environments. The results show that the SVR model based on the depth features extracted by SCAE has the best performance in predicting different Pb concentrations in silicon-free or silicon environments, and the coefficient of determination (Rp2), root mean square error (RMSEP) and residual predictive deviation (RPD) of prediction set in silicon-free or silicon environments were 0.9374, 0.02071 mg/kg and 3.268, and 0.9416, 0.01898 mg/kg and 3.316, respectively. Moreover, the SVR model based on the depth feature extracted by T-SCAE has the best performance in predicting different Pb concentrations in silicon-free and silicon environments, and the Rp2, RMSEP and RPD of the optimal prediction set were 0.9385, 0.02017 mg/kg and 3.291, respectively. The combination of hyperspectral fluorescence imaging and deep transfer learning algorithm can effectively detect different Pb concentrations in oilseed rape leaves in both non-silicon environment and silicon environment.
Assuntos
Brassica napus , Chumbo , Silício , Imageamento Hiperespectral , Análise dos Mínimos Quadrados , Algoritmos , Folhas de Planta , Aprendizado de MáquinaRESUMO
The tassel state in maize hybridization fields not only reflects the growth stage of the maize but also reflects the performance of the detasseling operation. Existing tassel detection models are primarily used to identify mature tassels with obvious features, making it difficult to accurately identify small tassels or detasseled plants. This study presents a novel approach that utilizes unmanned aerial vehicles (UAVs) and deep learning techniques to accurately identify and assess tassel states, before and after manually detasseling in maize hybridization fields. The proposed method suggests that a specific tassel annotation and data augmentation strategy is valuable for substantial enhancing the quality of the tassel training data. This study also evaluates mainstream object detection models and proposes a series of highly accurate tassel detection models based on tassel categories with strong data adaptability. In addition, a strategy for blocking large UAV images, as well as improving tassel detection accuracy, is proposed to balance UAV image acquisition and computational cost. The experimental results demonstrate that the proposed method can accurately identify and classify tassels at various stages of detasseling. The tassel detection model optimized with the enhanced data achieves an average precision of 94.5% across all categories. An optimal model combination that uses blocking strategies for different development stages can improve the tassel detection accuracy to 98%. This could be useful in addressing the issue of missed tassel detections in maize hybridization fields. The data annotation strategy and image blocking strategy may also have broad applications in object detection and recognition in other agricultural scenarios.
RESUMO
Biodegradable plastics promise eco-friendliness, yet their transformation into microplastics (bio-MPs) raises environmental alarms. However, how those bio-MPs affect the greenhouse gases (GHGs) and volatile organic compounds (VOCs) in soil ecosystems remains largely unexplored. Here, we investigated the effects of diverse bio-MPs (PBAT, PBS, and PLA) on GHGs and VOCs emission in typical paddy or upland soils. We monitored the carbon dioxide (CO2) and methane (CH4) fluxes in-situ using the self-developed portable optical gas sensor and analyzed VOC profiles using a proton-transfer reaction mass spectrometer (PTR-MS). Our study has revealed that, despite their biodegradable nature, bio-MPs do not always promote soil GHG emissions as previously thought. Specifically, PBAT and PLA significantly increased CO2 and CH4 emissions up to 1.9-7.5 and 115.9-178.5 fold, respectively, compared to the control group. While PBS exhibited the opposite trend, causing a decrease of up to 39.9% for CO2 and up to 39.9% for CH4. In addition, different types of bio-MPs triggered distinct soil VOC emission patterns. According to the Mann-Whitney U-test and Partial Least Squares Discriminant Analysis (PLS-DA), a recognizable VOC pattern associated with different bio-MPs was revealed. This study claims the necessity of considering polymer-specific responses when assessing the environmental impact of Bio-MPs, and providing insights into their implications for climate change.
Assuntos
Dióxido de Carbono , Metano , Microplásticos , Compostos Orgânicos Voláteis , Dióxido de Carbono/análise , Compostos Orgânicos Voláteis/análise , Metano/análise , Microplásticos/análise , Solo/química , Ecossistema , Poluentes do Solo/análise , Gases de Efeito Estufa/análise , Monitoramento Ambiental , Biodegradação Ambiental , Poluentes Atmosféricos/análiseRESUMO
In the process of feeding the distilling bucket after vapor detection, the existing methods can only realize the lag detection after the steam overflow, and can not accurately detect the location of the steam, etc. At the same time, in order to effectively reduce the occupancy of the computational resources and improve the deployment performance, this study established infrared image dataset of fermented grains surface, and fused the YOLO v5n and the knowledge distillation and the model pruning algorithms, and an lightweight method YOLO v5ns-DP was proposed as as a model for detecting temperature changes in the surface layer of fermented grains during the process of feeding the distilling. The experimental results indicated that the improvement makes YOLOv5n improve its performance in all aspects. The number of parameters, GLOPs and model size of YOLO v5ns-DP have been reduced by 28.6%, 16.5%, and 26.4%, respectively, and the mAP has been improved by 0.6. Therefore, the algorithm is able to predict in advance and accurately detect the location of the liquor vapor, which effectively improves the precision and speed of the detection of the temperature of the surface fermented grains , and well completes the real-time detecting task.
RESUMO
Excessive invalid explorations at the beginning of training lead deep reinforcement learning process to fall into the risk of overfitting, further resulting in spurious decisions, which obstruct agents in the following states and explorations. This phenomenon is termed primacy bias in online reinforcement learning. This work systematically investigates the primacy bias in online reinforcement learning, discussing the reason for primacy bias, while the characteristic of primacy bias is also analyzed. Besides, to learn a policy generalized to the following states and explorations, we develop an online reinforcement learning framework, termed self-distillation reinforcement learning (SDRL), based on knowledge distillation, allowing the agent to transfer the learned knowledge into a randomly initialized policy at regular intervals, and the new policy network is used to replace the original one in the following training. The core idea for this work is distilling knowledge from the trained policy to another policy can filter biases out, generating a more generalized policy in the learning process. Moreover, to avoid the overfitting of the new policy due to excessive distillations, we add an additional loss in the knowledge distillation process, using L2 regularization to improve the generalization, and the self-imitation mechanism is introduced to accelerate the learning on the current experiences. The results of several experiments in DMC and Atari 100k suggest the proposal has the ability to eliminate primacy bias for reinforcement learning methods, and the policy after knowledge distillation can urge agents to get higher scores more quickly.
RESUMO
Intermittent stop-move motion planning is essential for optimizing the efficiency of harvesting robots in greenhouse settings. Addressing issues like frequent stops, missed targets, and uneven task allocation, this study introduced a novel intermittent motion planning model using deep reinforcement learning for a dual-arm harvesting robot vehicle. Initially, the model gathered real-time coordinate data of target fruits on both sides of the robot, and projected these coordinates onto a two-dimensional map. Subsequently, the DDPG (Deep Deterministic Policy Gradient) algorithm was employed to generate parking node sequences for the robotic vehicle. A dynamic simulation environment, designed to mimic industrial greenhouse conditions, was developed to enhance the DDPG to generalize to real-world scenarios. Simulation results have indicated that the convergence performance of the DDPG model was improved by 19.82% and 33.66% compared to the SAC and TD3 models, respectively. In tomato greenhouse experiments, the model reduced vehicle parking frequency by 46.5% and 36.1% and decreased arm idleness by 42.9% and 33.9%, compared to grid-based and area division algorithms, without missing any targets. The average time required to generate planned paths was 6.9 ms. These findings demonstrate that the parking planning method proposed in this paper can effectively improve the overall harvesting efficiency and allocate tasks for a dual-arm harvesting robot in a more rational manner.
RESUMO
The Dezhou donkey is a famous local donkey breed in China. The aim of the present study was to identify the genes associated with the body size traits of the Dezhou donkey and facilitate the breeding activities of the donkeys. A total of 349 donkeys from two generations (113 individuals in F0 and 236 in F1) were analyzed with restriction-site associated DNA-sequencing. A genome-wide association study revealed that the region between 13.7 and 15.6 Mb of chromosome 13 is significantly associated with body sizes. Candidate genes related to body size development, including POLR2A, CHRNB1, FGF11, and ZBTB4, were identified. The results of GO and KEGG analysis indicated that the genes involved in many GO terms were related to metabolic processes and developmental processes. Additionally, a T>C mutation (Chr13:14312485) was found at intron 10 of the POLR2A gene. The association analysis showed significant differences among genotypes for the size traits. The body size of the individuals with the TT genotype was significantly higher than that with the CC genotype. The results showed that the polymorphism of POLR2A has the potential to be used as a marker in the breeding programs of the Dezhou donkeys.
RESUMO
Conventional methods for studying the plastic behavior of materials involve uniaxial tension and uniaxial compression. However, in the metal rolling process, the deformation zone undergoes a complex loading of multidirectional compression and shear. Characterizing the corresponding plastic evolution process online poses challenges, and the existing specimen structures struggle to accurately replicate the deformation-induced loading characteristics. In this study, we aimed to design a compression-shear composite loading specimen that closely mimics the actual processing conditions. The goal was to investigate how the specimen structure influences the stress-strain response in the deformation zone. Using commercial finite element software, a compression-shear composite loading specimen was meticulously designed. Five 304 stainless steel specimens underwent uniaxial compressive loading, with variation angles between the preset notch angle (PNA) of the specimen and compression direction. We employed digital image correlation methods to capture the impact of the PNA on the strain field during compression. Additionally, we aimed to elucidate the plastic response resulting from the stress state of the specimen, particularly in relation to specimen fracture and microstructural evolution.
RESUMO
Palmitic acid (PA) is a kind of saturated high fatty acid, which is involved in physiological safety and food quality. A surface molecularly imprinted polymer (MIP) electrochemical sensor was prepared on MXene surface using dopamine (DA) as functional monomer. The electrode was modified with gold nanoparticles (AuNPs), ferrocene-graphene oxide-multiwalled carbon nanotubes (Fc-GO-MWCNT) composite to enhance the electroactive area and conductivity. The sensor was characterized by scanning electron microscope (SEM), energy-dispersive X-ray spectroscopy (EDS), electrochemical impedance spectroscopy (EIS) and Differential pulse voltammetry (DPV), respectively. The parameters concerning this assay and various regeneration conditions have been carefully studied. The sensor can detect PA in the range of 1 nM-1 mM (R2 = 0.995), the limit of detection (LOD) is 0.48 nM (S/N = 3), and the limit of quantification (LOQ) is 1.61 nM. The artificial neural network (ANN) model in machine learning is further used to analyze the data collected by the sensor. The results show that the back propagation (BP) neural network in ANN is more suitable for the intelligent analysis of PA. The practicality of the sensor was confirmed by detecting PA in pork samples. This is the first MIP-based electrochemical sensor for PA, and it has great potential in practical applications.
Assuntos
Técnicas Eletroquímicas , Ouro , Grafite , Aprendizado de Máquina , Nanopartículas Metálicas , Nanotubos de Carbono , Ácido Palmítico , Grafite/química , Ouro/química , Nanotubos de Carbono/química , Técnicas Eletroquímicas/métodos , Técnicas Eletroquímicas/instrumentação , Ácido Palmítico/análise , Ácido Palmítico/química , Nanopartículas Metálicas/química , Eletrodos , Polímeros Molecularmente Impressos/química , Impressão Molecular , Animais , Propriedades de Superfície , Dopamina/análise , Compostos Ferrosos/química , Limite de Detecção , Redes Neurais de Computação , Metalocenos/químicaRESUMO
Tomatoes are prone to mechanical damage due to improper gripping forces during automated harvest and postharvest processes. To reduce this damage, a dynamic viscoelastic model based on long short-term memory (LSTM) is proposed to fit the dynamic compression stress relaxation characteristics of the individual fruit. Furthermore, the classical stress relaxation models involved, the triple-element Maxwell and Caputo fractional derivative models, are compared with the LSTM model to validate its performance. Meanwhile, the LSTM and classical stress relaxation models are used to predict the stress relaxation characteristics of tomato fruit with different fruit sizes and compression positions. The results for the whole test dataset show that the LSTM model achieves a RMSE of 2.829×10-5 Mpa and a MAPE of 0.228%. It significantly outperforms the Caputo fractional derivative model by demonstrating a substantial enhancement with a 37% decrease in RMSE and a 36% reduction in MAPE. Further analysis of individual tomato fruit reveals the LSTM model's performance, with the minimum RMSE recorded at the septum position being 3.438×10-5 Mpa, 31% higher than the maximum RMSE at the locule position. Similarly, the lowest MAPE at the septum stands at 0.375%, outperforming the highest MAPE at the locule position by a significant margin of 90%. Moreover, the LSTM model consistently reports the smallest discrepancies between the predicted and observed values compared to classical stress relaxation models. This accuracy suggests that the LSTM model could effectively supplant classical stress relaxation models for predicting stress relaxation changes in individual tomato fruit.
RESUMO
Gallic acid (GA) is one of the main phenolic components naturally occurring in many plants and foods and has been a subject of increasing interest owing to its antioxidant and anti-mutagenic properties. This study introduces a novel flexible sensor designed for in situ detecting GA in plant leaves. The sensor employs a laser-induced graphene (LIG) flexible electrode, enhanced with MXene and molybdenum disulfide (MoS2) nanosheets. The MXene/MoS2/LIG flexible sensor not only demonstrates exceptional mechanical properties, covering a wide detection range of 1-1000 µM for GA, but also exhibits remarkable selectivity and stability. The as-prepared sensor was successfully applied to in situ determination of GA content in strawberry leaves under salt stress. This innovative sensor opens an attractive avenue for in situ measurement of metabolites in plant bodies with flexible electronics.
RESUMO
The polymer liner of the hydrogen storage cylinder was studied to investigate better hydrogen storage capacity in Type-IV cylinders. Molecular dynamics methods were used to simulate the adsorption and diffusion processes of hydrogen in a graphene-filled polyamide 6 (PA6) system. The solubility and diffusion characteristics of hydrogen in PA6 systems filled with different filler ratios (3 wt%, 4 wt%, 5 wt%, 6 wt%, and 7 wt%) were studied under working pressures (0.1 MPa, 35 MPa, 52 MPa, and 70 MPa). The effects of filler ratio, temperature, and pressure on hydrogen diffusion were analyzed. The results show that at atmospheric pressure when the graphene content reaches 5 wt%, its permeability coefficient is as low as 2.44 × 10-13 cm3·cm/(cm2·s·Pa), which is a 54.6% reduction compared to PA6. At 358 K and 70 MPa, the diffusion coefficient of the 5 wt% graphene/PA6 composite system is 138% higher than that at 298 K and 70 MPa. With increasing pressure, the diffusion coefficients of all materials generally decrease linearly. Among them, pure PA6 has the largest diffusion coefficient, while the 4 wt% graphene/PA6 composite system has the smallest diffusion coefficient. Additionally, the impact of FFV (free volume fraction) on the barrier properties of the material was studied, and the movement trajectory of H2 in the composite system was analyzed.
RESUMO
The radiation use efficiency (RUE) is one of the most important functional traits determining crop productivity. The coordination of the vertical distribution of light and leaf nitrogen has been proven to be effective in boosting the RUE from both experimental and computational evidence. However, previous simulation studies have primarily assumed that the leaf area is uniformly distributed along the canopy depth, rarely considering the optimization of the leaf area distribution, especially for C4 crops. The present study hypothesizes that the RUE may be maximized by matching the leaf area and leaf nitrogen vertical distributions in the canopy. To test this hypothesis, various virtual maize canopies were generated by combining the leaf inclination angle, vertical leaf area distribution, and vertical leaf nitrogen distribution and were further evaluated by an improved multilayer canopy photosynthesis model. We found that a greater fraction of leaf nitrogen is preferentially allocated to canopy layers with greater leaf areas to maximize the RUE. The coordination of light and nitrogen emerged as a property from the simulations to maximize the RUE in most scenarios, particularly in dense canopies. This study not only facilitates explicit and precise profiling of ideotypes for maximizing the RUE but also represents a primary step toward high-throughput phenotyping and screening of the RUE for massive numbers of inbred lines and cultivars.
RESUMO
It is of great significance to study the plant morphological structure for improving crop yield and achieving efficient use of resources. Three dimensional (3D) information can more accurately describe the morphological and structural characteristics of crop plants. Automatic acquisition of 3D information is one of the key steps in plant morphological structure research. Taking wheat as the research object, we propose a point cloud data-driven 3D reconstruction method that achieves 3D structure reconstruction and plant morphology parameterization at the phytomer scale. Specifically, we use the MVS-Pheno platform to reconstruct the point cloud of wheat plants and segment organs through the deep learning algorithm. On this basis, we automatically reconstructed the 3D structure of leaves and tillers and extracted the morphological parameters of wheat. The results show that the semantic segmentation accuracy of organs is 95.2%, and the instance segmentation accuracy AP50 is 0.665. The R2 values for extracted leaf length, leaf width, leaf attachment height, stem leaf angle, tiller length, and spike length were 0.97, 0.80, 1.00, 0.95, 0.99, and 0.95, respectively. This method can significantly improve the accuracy and efficiency of 3D morphological analysis of wheat plants, providing strong technical support for research in fields such as agricultural production optimization and genetic breeding.
RESUMO
Fermentation is the key process to determine the quality of black tea. Traditional physical and chemical analyses are time consuming, it cannot meet the needs of online monitoring. The existing rapid testing techniques cannot determine the specific volatile organic compounds (VOCs) produced at different stages of fermentation, resulting in poor model transferability; therefore, the current degree of black tea fermentation mainly relies on the sensory judgment of tea makers. This study used proton transfer reaction mass spectrometry (PTR-MS) and fourier transform infrared spectroscopy (FTIR) combined with different injection methods to collect VOCs of the samples, the rule of change of specific VOCs was clarified, and the extreme learning machine (ELM) model was established after principal component analysis (PCA), the prediction accuracy reached 95% and 100%, respectively. Finally, different application scenarios of the two technologies in the actual production of black tea are discussed based on their respective advantages.
Assuntos
Camellia sinensis , Fermentação , Espectrometria de Massas , Chá , Compostos Orgânicos Voláteis , Compostos Orgânicos Voláteis/química , Compostos Orgânicos Voláteis/análise , Chá/química , Espectrometria de Massas/métodos , Camellia sinensis/química , Camellia sinensis/metabolismo , Espectroscopia de Infravermelho com Transformada de Fourier/métodos , Análise de Componente PrincipalRESUMO
OBJECTIVES: Hypervirulent carbapenem-resistant Klebsiella pneumoniae (hv-CRKp) poses a significant threat to public health. This study reports an infection related to hv-CRKp in a premature infant and reveals its colistin resistance and evolutionary mechanisms within the host. METHODS: Three KPC-producing CRKp strains were isolated from a patient with sepsis and CRKp osteoarthritis who had been receiving colistin antimicrobial therapy. The minimum inhibitory concentrations (MICs) of ceftazidime, ceftazidime-avibactam (CAZ-AVI), meropenem, imipenem, tigecycline, amikacin, minocycline, sulfamethoxazole/trimethoprim, ciprofloxacin, levofloxacin, aztreonam, cefepime, cefoperazone/sulbactam, piperacillin/tazobactam, and colistin were determined using the microbroth dilution method. The whole-genome sequencing analysis was conducted to determine the sequence types (STs), virulence genes, and antibiotic resistance genes of the three CRKp strains. RESULTS: Whole-genome sequencing revealed that all three CRKp strains belonged to the ST11 clone and carried a plasmid encoding blaKPC-2. The three strains all possessed the iucABCDiutA virulence cluster, peg-344 gene, and rmpA/rmpA2 genes, defining them as hv-CRKp. Further experiments and whole-genome analysis revealed that a strain of K. pneuomniae had developed resistance to colistin. The mechanism found to be responsible for colistin resistance was a deletion mutation of approximately 9000 bp including the mgrB gene. CONCLUSION: This study characterizes colistin resistance of the ST11 clone hv-CRKp during colistin treatment and its rapid evolution within the host.
RESUMO
Yield prediction is the primary goal of genomic selection (GS)-assisted crop breeding. Because yield is a complex quantitative trait, making predictions from genotypic data is challenging. Transfer learning can produce an effective model for a target task by leveraging knowledge from a different, but related, source domain and is considered a great potential method for improving yield prediction by integrating multi-trait data. However, it has not previously been applied to genotype-to-phenotype prediction owing to the lack of an efficient implementation framework. We therefore developed TrG2P, a transfer-learning-based framework. TrG2P first employs convolutional neural networks (CNN) to train models using non-yield-trait phenotypic and genotypic data, thus obtaining pre-trained models. Subsequently, the convolutional layer parameters from these pre-trained models are transferred to the yield prediction task, and the fully connected layers are retrained, thus obtaining fine-tuned models. Finally, the convolutional layer and the first fully connected layer of the fine-tuned models are fused, and the last fully connected layer is trained to enhance prediction performance. We applied TrG2P to five sets of genotypic and phenotypic data from maize (Zea mays), rice (Oryza sativa), and wheat (Triticum aestivum) and compared its model precision to that of seven other popular GS tools: ridge regression best linear unbiased prediction (rrBLUP), random forest, support vector regression, light gradient boosting machine (LightGBM), CNN, DeepGS, and deep neural network for genomic prediction (DNNGP). TrG2P improved the accuracy of yield prediction by 39.9%, 6.8%, and 1.8% in rice, maize, and wheat, respectively, compared with predictions generated by the best-performing comparison model. Our work therefore demonstrates that transfer learning is an effective strategy for improving yield prediction by integrating information from non-yield-trait data. We attribute its enhanced prediction accuracy to the valuable information available from traits associated with yield and to training dataset augmentation. The Python implementation of TrG2P is available at https://github.com/lijinlong1991/TrG2P. The web-based tool is available at http://trg2p.ebreed.cn:81.