pith. sign in

arxiv: 2605.23478 · v1 · pith:O2DWS4XGnew · submitted 2026-05-22 · 💻 cs.CV · cs.AI

PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction

Yu Luo , Xiaogang Zhu , Shan Zeng , Wei Xiang , Thomas Francis Bishop , Zhiyong Wang , Kun Hu This is my paper

Pith reviewed 2026-05-25 04:30 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords crop yield predictionphenological responsesmulti-cropattention mechanismtemporal modelingself-supervised learningweather driversgeneralization
0
0 comments X

The pith

PhenoYieldNet predicts yields for many crops by learning each crop's unique phenological response to weather patterns.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Existing yield prediction methods typically focus on one crop at a time and fail to generalize when weather affects different crops in unique ways. PhenoYieldNet addresses this by building a decoder that maintains a bank of learnable phenology patterns for various crops and uses an attention module to select and combine multi-scale patterns according to weather inputs. The approach also adapts a pre-trained encoder with self-supervised contrastive learning tailored to temporal agricultural data. A sympathetic reader would care because accurate multi-crop forecasts could support better planning for food production across diverse agricultural systems. Experiments on multiple datasets demonstrate improved performance and generalization to new regions and crops.

Core claim

PhenoYieldNet is a multi-crop yield prediction framework that learns crop-specific phenology by explicitly modeling their responses with temporal drivers through a crop-aware temporal decoder consisting of a Crop Phenology Bank and a Crop Phenology Attention module, with the encoder adapted via self-supervised Temporal Contrastive Adaptation, leading to significant outperformance of state-of-the-art methods with strong generalization across regions and crops.

What carries the argument

The Crop Phenology Bank (CPB) of learnable embeddings and Crop Phenology Attention (CPA) module, which use queries to guide selection and integration of multi-scale trend and variation components from temporal weather inputs for each crop.

If this is right

  • A single framework can handle yield prediction for diverse crop types without separate models.
  • The attention mechanism allows dynamic adjustment to relevant phenological stages based on weather.
  • Pre-training and contrastive adaptation produce features that align with agricultural temporal dynamics.
  • The method shows strong generalization to different regions and crops.
  • Overall prediction accuracy exceeds that of existing single-crop approaches.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If correct, yield prediction systems could shift from crop-specific to crop-aware unified models.
  • The explicit separation of trend and variation components may enable finer analysis of weather effects on growth phases.
  • Success with the foundation model adaptation suggests similar transfer could work for other time-series tasks in agriculture.

Load-bearing premise

A set of learnable embeddings in the Crop Phenology Bank combined with the Crop Phenology Attention module can dynamically capture and adjust to the most relevant multi-scale phenological patterns for each specific crop when driven by temporal weather inputs.

What would settle it

Evaluation on a new crop type or geographic region where the PhenoYieldNet model fails to outperform state-of-the-art single-crop methods or exhibits poor generalization performance.

Figures

Figures reproduced from arXiv: 2605.23478 by Kun Hu, Shan Zeng, Thomas Francis Bishop, Wei Xiang, Xiaogang Zhu, Yu Luo, Zhiyong Wang.

Figure 1
Figure 1. Figure 1: (a) Existing yield prediction methods typically train a [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the PhenoYieldNet architecture. A multimodal encoder processes satellite image time series ( [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Illustration of Crop Phenology Attention module. [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Yield prediction error distribution for corn across four U.S. states. correlation scores. Specifically, for soybean, our method achieves the lowest RMSE of 6.22 and the highest corre￾lation metrics, with R2 = 0.627 and Corr = 0.792. For corn, compared to the second-best method (i.e., RF), Phe￾noYieldNet reduces RMSE by 4.69 and improves R2 and Corr by 0.085 and 0.038, respectively. These superior re￾sults … view at source ↗
Figure 5
Figure 5. Figure 5: RMSE of real-time multi-crop yield prediction. [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: RMSE in stable vs. volatile weather regions. [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
read the original abstract

Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for single-crop prediction, they often struggle to generalize across diverse crop types, without addressing the unique crop phenological responses that are dynamically modulated by complex weather patterns. In this paper, we propose PhenoYieldNet, a multi-crop yield prediction framework that learns crop-specific phenology by explicitly modeling their responses with temporal drivers. Specifically, we develop a crop-aware temporal decoder consisting of a Crop Phenology Bank (CPB) and a Crop Phenology Attention (CPA) module. The CPB integrates a set of learnable embeddings, which leverage a query to guide the CPA module to learn the most relevant phenology patterns for the specific crop. And the CPA module explicitly captures multi-scale trend and variation components to construct temporal contexts, enabling the model to dynamically adjust the attention across different phenological stages. To learn robust and generalizable features for multi-crop prediction, the encoder is initialized with a pre-trained foundation model, and further adapted via a self-supervised Temporal Contrastive Adaptation strategy to align with agricultural temporal dynamics. Extensive experiments conducted on multi-crop datasets indicate that our proposed method significantly outperforms state-of-the-art methods, exhibiting strong generalization capabilities across different regions and crops.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes PhenoYieldNet, a multi-crop yield prediction framework featuring a crop-aware temporal decoder with a Crop Phenology Bank (CPB) containing learnable embeddings and a Crop Phenology Attention (CPA) module that captures multi-scale trend and variation components from temporal weather inputs. The encoder is initialized from a pre-trained foundation model and adapted via self-supervised Temporal Contrastive Adaptation. The central claim is that this architecture significantly outperforms state-of-the-art methods while exhibiting strong generalization across regions and crops, based on experiments on multi-crop datasets.

Significance. If the performance and generalization claims hold after proper validation, the work could advance multi-crop modeling by explicitly addressing crop-specific phenological dynamics rather than treating all crops uniformly, which is relevant to agricultural forecasting and food security applications.

major comments (1)
  1. [Abstract] Abstract: The assertion that the method 'significantly outperforms state-of-the-art methods' and shows 'strong generalization capabilities across different regions and crops' is presented without any dataset descriptions, baseline comparisons, quantitative results, statistical tests, or ablation studies. This absence is load-bearing for the central empirical claim of the paper.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the careful review and for identifying an important point regarding the abstract. We address the comment below and propose a revision.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion that the method 'significantly outperforms state-of-the-art methods' and shows 'strong generalization capabilities across different regions and crops' is presented without any dataset descriptions, baseline comparisons, quantitative results, statistical tests, or ablation studies. This absence is load-bearing for the central empirical claim of the paper.

    Authors: We agree that the abstract, as currently written, presents the performance claims without the supporting details listed. The full manuscript contains these elements: dataset descriptions and preprocessing in Section 4.1, baseline methods and quantitative results (including statistical significance tests) in Section 4.2 and Table 2, ablation studies in Section 4.3, and cross-region/cross-crop generalization experiments in Section 4.4. To directly address the concern, we will revise the abstract to include concise references to the multi-crop datasets, key quantitative improvements (e.g., average yield prediction gains), and mention of the ablation and generalization analyses. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The provided abstract and description contain no equations, derivation steps, or self-citations that could be inspected for reduction to inputs by construction. The model components (CPB with learnable embeddings, CPA module, pre-trained encoder, temporal contrastive adaptation) are presented as architectural choices without any claimed first-principles derivation or uniqueness theorem. Claims of outperformance and generalization rest on experimental results rather than any internal mathematical chain that loops back to fitted parameters or self-referential definitions. This is the standard case of a self-contained empirical ML paper where no load-bearing circularity is detectable from the given text.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No equations, methods sections, or implementation details are available from the abstract, so free parameters, axioms, and invented entities cannot be identified.

pith-pipeline@v0.9.0 · 5778 in / 1145 out tokens · 23979 ms · 2026-05-25T04:30:43.099306+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

47 extracted references · 6 canonical work pages · 4 internal anchors

  1. [1]

    Deep density estimation based on multi-spectral remote sensing data for in-field crop yield forecasting

    Liana Baghdasaryan, Razmik Melikbekyan, Arthur Dolma- jain, and Jennifer Hobbs. Deep density estimation based on multi-spectral remote sensing data for in-field crop yield forecasting. InIEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2014–2023, 2022. 2

    2014

  2. [2]

    Random forests.Machine learning, 45(1): 5–32, 2001

    Leo Breiman. Random forests.Machine learning, 45(1): 5–32, 2001. 5, 7

    2001

  3. [3]

    Target-aware yield prediction (tayp) model used to improve agriculture crop productivity.IEEE Transactions on Geoscience and Remote Sensing, 62:1–11,

    Yen-Jen Chang, Ming-Hsin Lai, Chien-Ho Wang, Yu-Shun Huang, and Jason Lin. Target-aware yield prediction (tayp) model used to improve agriculture crop productivity.IEEE Transactions on Geoscience and Remote Sensing, 62:1–11,

  4. [4]

    Xgboost: A scalable tree boosting system

    Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. InProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794, 2016. 5, 7

    2016

  5. [5]

    Satmae: Pre-training transformers for tem- poral and multi-spectral satellite imagery.Advances in Neu- ral Information Processing Systems, 35:197–211, 2022

    Yezhen Cong, Samar Khanna, Chenlin Meng, Patrick Liu, Erik Rozi, Yutong He, Marshall Burke, David Lobell, and Stefano Ermon. Satmae: Pre-training transformers for tem- poral and multi-spectral satellite imagery.Advances in Neu- ral Information Processing Systems, 35:197–211, 2022. 3

    2022

  6. [6]

    One-dm: One-shot diffusion mimicker for handwritten text generation

    Gang Dai, Yifan Zhang, Quhui Ke, Qiangya Guo, and Shuangping Huang. One-dm: One-shot diffusion mimicker for handwritten text generation. InEuropean Conference on Computer Vision, pages 410–427, 2024. 2

    2024

  7. [7]

    Vg-sam: Visual in-context guided sam for universal medical image segmentation.Fractal and Frac- tional, 9(11):722, 2025

    Gang Dai, Qingfeng Wang, Yutao Qin, Gang Wei, and Shuangping Huang. Vg-sam: Visual in-context guided sam for universal medical image segmentation.Fractal and Frac- tional, 9(11):722, 2025. 2

    2025

  8. [8]

    Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities

    Jingtong Dou, Chuancheng Shi, Jian Wang, Fei Shen, Zhiy- ong Wang, and Tat-Seng Chua. Beyond surface artifacts: Capturing shared latent forgery knowledge across modali- ties.arXiv preprint arXiv:2604.07763, 2026. 3

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  9. [9]

    A gnn-rnn approach for harnessing geospa- tial and temporal information: application to crop yield pre- diction

    Joshua Fan, Junwen Bai, Zhiyun Li, Ariel Ortiz-Bobea, and Carla P Gomes. A gnn-rnn approach for harnessing geospa- tial and temporal information: application to crop yield pre- diction. InAAAI conference on artificial intelligence, pages 11873–11881, 2022. 2

    2022

  10. [10]

    Enhancing crop segmentation in satellite image time-series with transformer networks

    Ignazio Gallo, Mattia Gatti, Nicola Landro, Christian Loschiavo, Mirco Boschetti, Riccardo La Grassa, and An- war Ur Rehman. Enhancing crop segmentation in satellite image time-series with transformer networks. InInterna- tional Conference on Machine Vision (ICMV), pages 62–69. SPIE, 2024. 3

    2024

  11. [11]

    Red fox optimization with ensemble recurrent neural network for crop recommendation and yield prediction model.Multimedia Tools and Applica- tions, 83(5):13159–13179, 2024

    PSS Gopi and M Karthikeyan. Red fox optimization with ensemble recurrent neural network for crop recommendation and yield prediction model.Multimedia Tools and Applica- tions, 83(5):13159–13179, 2024. 2

    2024

  12. [12]

    Fengwei Guo, Pengxin Wang, Kevin Tansey, Yue Zhang, Mingqi Li, Junming Liu, and Shuyu Zhang. A novel transformer-based neural network under model interpretabil- ity for improving wheat yield estimation using remotely sensed multi-variables.Computers and Electronics in Agri- culture, 223:109111, 2024. 3

    2024

  13. [13]

    Skysense: A multi-modal remote sensing foundation model towards universal interpretation for earth observation imagery

    Xin Guo, Jiangwei Lao, Bo Dang, Yingying Zhang, Lei Yu, Lixiang Ru, Liheng Zhong, Ziyuan Huang, Kang Wu, Dingxiang Hu, et al. Skysense: A multi-modal remote sensing foundation model towards universal interpretation for earth observation imagery. InIEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 27672– 27683, 2024. 3

    2024

  14. [14]

    Physics guided neural networks for time-aware fairness: an application in crop yield prediction

    Erhu He, Yiqun Xie, Licheng Liu, Weiye Chen, Zhenong Jin, and Xiaowei Jia. Physics guided neural networks for time-aware fairness: an application in crop yield prediction. InAAAI conference on artificial intelligence, pages 14223– 14231, 2023. 1

    2023

  15. [15]

    An operational approach to large-scale crop yield prediction with spatio-temporal ma- chine learning models

    Patrick Helber, Benjamin Bischke, Carolin Packbier, Peter Habelitz, and Florian Seefeldt. An operational approach to large-scale crop yield prediction with spatio-temporal ma- chine learning models. InIGARSS IEEE International Geo- science and Remote Sensing Symposium, pages 4299–4302. IEEE, 2024. 5, 6, 7

    2024

  16. [16]

    Spectralgpt: Spectral remote sensing foun- dation model.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8):5227–5244, 2024

    Danfeng Hong, Bing Zhang, Xuyang Li, Yuxuan Li, Chenyu Li, Jing Yao, Naoto Yokoya, Hao Li, Pedram Ghamisi, Xi- uping Jia, et al. Spectralgpt: Spectral remote sensing foun- dation model.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8):5227–5244, 2024. 3

    2024

  17. [17]

    Impact of future cli- mate trend and fluctuation on winter wheat yield in the north china plain and adaptation strategies.Scientific Reports, 15 (1):21882, 2025

    Jinpeng Hu, Yichen Li, and Peijun Shi. Impact of future cli- mate trend and fluctuation on winter wheat yield in the north china plain and adaptation strategies.Scientific Reports, 15 (1):21882, 2025. 2

    2025

  18. [18]

    Random forests for global and regional crop yield predictions.PloS one, 11(6):e0156571, 2016

    Jig Han Jeong, Jonathan P Resop, Nathaniel D Mueller, David H Fleisher, Kyungdahm Yun, Ethan E Butler, Dennis J Timlin, Kyo-Moon Shim, James S Gerber, Vangimalla R Reddy, et al. Random forests for global and regional crop yield predictions.PloS one, 11(6):e0156571, 2016. 2

    2016

  19. [19]

    Sungha Ju, Hyoungjoon Lim, Jong Won Ma, Soohyun Kim, Kyungdo Lee, Shuhe Zhao, and Joon Heo. Optimal county- level crop yield prediction using modis-based variables and weather data: A comparative study on machine learning models.Agricultural and Forest Meteorology, 307:108530,

  20. [20]

    Hamid Kamangir, Brent S Sams, Nick Dokoozlian, Luis Sanchez, and J Mason Earles. Large-scale spatio-temporal yield estimation via deep learning using satellite and man- agement data fusion in vineyards.Computers and Electron- ics in Agriculture, 216:108439, 2024. 2, 5, 6, 7

    2024

  21. [21]

    A generalized multimodal deep learning model for early crop yield prediction

    Arshveer Kaur, Poonam Goyal, Kartik Sharma, Lakshay Sharma, and Navneet Goyal. A generalized multimodal deep learning model for early crop yield prediction. InIEEE In- ternational Conference on Big Data (Big Data), pages 1272–

  22. [22]

    A cnn-rnn framework for crop yield prediction.Frontiers in Plant Science, 10:1750, 2020

    Saeed Khaki, Lizhi Wang, and Sotirios V Archontoulis. A cnn-rnn framework for crop yield prediction.Frontiers in Plant Science, 10:1750, 2020. 2

    2020

  23. [23]

    Simultaneous corn and soybean yield prediction from remote sensing data using deep transfer learning.Scientific Reports, 11(1):11132,

    Saeed Khaki, Hieu Pham, and Lizhi Wang. Simultaneous corn and soybean yield prediction from remote sensing data using deep transfer learning.Scientific Reports, 11(1):11132,

  24. [24]

    Mmst-vit: Climate change- aware crop yield prediction via multi-modal spatial-temporal vision transformer

    Fudong Lin, Summer Crawford, Kaleb Guillot, Yihe Zhang, Yan Chen, Xu Yuan, Li Chen, Shelby Williams, Robert Min- vielle, Xiangming Xiao, et al. Mmst-vit: Climate change- aware crop yield prediction via multi-modal spatial-temporal vision transformer. InIEEE/CVF International Conference on Computer Vision, pages 5774–5784, 2023. 2, 5, 6, 7

    2023

  25. [25]

    Rice yield prediction and model interpretation based on satellite and cli- matic indicators using a transformer method.Remote Sens- ing, 14(19):5045, 2022

    Yuanyuan Liu, Shaoqiang Wang, Jinghua Chen, Bin Chen, Xiaobo Wang, Dongze Hao, and Leigang Sun. Rice yield prediction and model interpretation based on satellite and cli- matic indicators using a transformer method.Remote Sens- ing, 14(19):5045, 2022. 3

    2022

  26. [26]

    SGDR: stochastic gradient descent with warm restarts

    Ilya Loshchilov and Frank Hutter. SGDR: stochastic gradient descent with warm restarts. InInternational Conference on Learning Representations, ICLR, 2017. 6

    2017

  27. [27]

    Decoupled Weight Decay Regularization

    Ilya Loshchilov, Frank Hutter, et al. Fixing weight decay regularization in adam.arXiv preprint arXiv:1711.05101, 5: 5, 2017. 6

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  28. [28]

    Goa-optimized deep learning for soybean yield estima- tion using multi-source remote sensing data.Scientific Re- ports, 14(1):7097, 2024

    Jian Lu, Hongkun Fu, Xuhui Tang, Zhao Liu, Jujian Huang, Wenlong Zou, Hui Chen, Yue Sun, Xiangyu Ning, and Jian Li. Goa-optimized deep learning for soybean yield estima- tion using multi-source remote sensing data.Scientific Re- ports, 14(1):7097, 2024. 2

    2024

  29. [29]

    Context-aware deep representation learning for geo-spatiotemporal analysis

    Hanzi Mao, Xi Liu, Nick Duffield, Hao Yuan, Shuiwang Ji, and Binayak Mohanty. Context-aware deep representation learning for geo-spatiotemporal analysis. InIEEE Interna- tional Conference on Data Mining (ICDM), pages 392–401. IEEE, 2020. 2, 3

    2020

  30. [30]

    Adaptive fusion of multi-modal remote sensing data for op- timal sub-field crop yield prediction.Remote Sensing of En- vironment, 318:114547, 2025

    Francisco Mena, Deepak Pathak, Hiba Najjar, Cristhian Sanchez, Patrick Helber, Benjamin Bischke, Peter Habelitz, Miro Miranda, Jayanth Siddamsetty, Marlon Nuske, et al. Adaptive fusion of multi-modal remote sensing data for op- timal sub-field crop yield prediction.Remote Sensing of En- vironment, 318:114547, 2025. 2, 3, 5, 6, 7

    2025

  31. [31]

    Temporal convolutional network based rice crop yield prediction using multispectral satellite data.Infrared Physics & Technology, 135:104960, 2023

    Alkha Mohan, M Venkatesan, P Prabhavathy, and A Jayakr- ishnan. Temporal convolutional network based rice crop yield prediction using multispectral satellite data.Infrared Physics & Technology, 135:104960, 2023. 3

    2023

  32. [32]

    Seyed Mahdi Mirhoseini Nejad, Dariush Abbasi- Moghadam, Alireza Sharifi, Nizom Farmonov, Khilola Amankulova, and Mucsi L ´aszl´z. Multispectral crop yield prediction using 3d-convolutional neural networks and attention convolutional lstm approaches.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16:254–266, 2022. 3

    2022

  33. [33]

    Crop yield prediction with deep convolutional neural net- works.Computers and Electronics in Agriculture, 163: 104859, 2019

    Petteri Nevavuori, Nathaniel Narra, and Tarmo Lipping. Crop yield prediction with deep convolutional neural net- works.Computers and Electronics in Agriculture, 163: 104859, 2019. 2

    2019

  34. [34]

    Rethinking transformers pre-training for multi- spectral satellite imagery

    Mubashir Noman, Muzammal Naseer, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, and Fahad Shah- baz Khan. Rethinking transformers pre-training for multi- spectral satellite imagery. InIEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 27811–27819,

  35. [35]

    Gener- alized classification of satellite image time series with ther- mal positional encoding

    Joachim Nyborg, Charlotte Pelletier, and Ira Assent. Gener- alized classification of satellite image time series with ther- mal positional encoding. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1392–1402, 2022. 2

    2022

  36. [36]

    Global gridded crop production dataset at 10 km resolution from 2010 to 2020.Scientific Data, 11(1):1377,

    Xingli Qin, Bingfang Wu, Hongwei Zeng, Miao Zhang, and Fuyou Tian. Global gridded crop production dataset at 10 km resolution from 2010 to 2020.Scientific Data, 11(1):1377,

    2010

  37. [37]

    Climate change impacts on crop yields.Nature Reviews Earth & Environment, 4(12): 831–846, 2023

    Ehsan Eyshi Rezaei, Heidi Webber, Senthold Asseng, Ken- neth Boote, Jean Louis Durand, Frank Ewert, Pierre Martre, and Dilys Sefakor MacCarthy. Climate change impacts on crop yields.Nature Reviews Earth & Environment, 4(12): 831–846, 2023. 1, 2

    2023

  38. [38]

    Where culture fades: Revealing the cultural gap in text-to-image generation.arXiv preprint arXiv:2511.17282, 2025

    Chuancheng Shi, Shangze Li, Shiming Guo, Simiao Xie, Wenhua Wu, Jingtong Dou, Chao Wu, Canran Xiao, Cong Wang, Zifeng Cheng, et al. Where culture fades: Revealing the cultural gap in text-to-image generation.arXiv preprint arXiv:2511.17282, 2025. 3

    work page arXiv 2025

  39. [39]

    Ri-mae: Rotation- invariant masked autoencoders for self-supervised point cloud representation learning

    Kunming Su, Qiuxia Wu, Panpan Cai, Xiaogang Zhu, Xue- quan Lu, Zhiyong Wang, and Kun Hu. Ri-mae: Rotation- invariant masked autoencoders for self-supervised point cloud representation learning. InProceedings of the AAAI Conference on Artificial Intelligence, pages 7015–7023,

  40. [40]

    County-level soybean yield prediction using deep cnn- lstm model.Sensors, 19(20):4363, 2019

    Jie Sun, Liping Di, Ziheng Sun, Yonglin Shen, and Zulong Lai. County-level soybean yield prediction using deep cnn- lstm model.Sensors, 19(20):4363, 2019. 2

    2019

  41. [41]

    An empirical study of remote sensing pretraining.IEEE Transactions on Geoscience and Remote Sensing, 61:1–20,

    Di Wang, Jing Zhang, Bo Du, Gui-Song Xia, and Dacheng Tao. An empirical study of remote sensing pretraining.IEEE Transactions on Geoscience and Remote Sensing, 61:1–20,

  42. [42]

    Duocast: Duo-probabilistic diffusion for precipitation nowcasting.arXiv preprint arXiv:2412.01091, 2024

    Penghui Wen, Mengwei He, Patrick Filippi, Na Zhao, Feng Zhang, Thomas Francis Bishop, Zhiyong Wang, and Kun Hu. Duocast: Duo-probabilistic diffusion for precipitation nowcasting.arXiv preprint arXiv:2412.01091, 2024. 2

    work page arXiv 2024

  43. [43]

    Stable Attention Response for Reliable Precipitation Nowcasting

    Penghui Wen, Zexin Hu, Sen Zhang, Patrick Filippi, Xiao- gang Zhu, Allen Benter, Thomas Bishop, Zhiyong Wang, and Kun Hu. Stable attention response for reliable precip- itation nowcasting.arXiv preprint arXiv:2605.13181, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  44. [44]

    McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting

    Penghui Wen, Yu Luo, Lintao Wang, Mengwei He, Patrick Filippi, Thomas Francis Bishop, and Zhiyong Wang. Mc- cast: Memory-guided latent drift correction for long-horizon precipitation nowcasting.arXiv preprint arXiv:2605.13197,

    work page internal anchor Pith review Pith/arXiv arXiv

  45. [45]

    Suraj A Yadav, Xin Zhang, Nuwan K Wijewardane, Max Feldman, Ruijun Qin, Yanbo Huang, Sathishkumar Samiap- pan, Wyatt Young, and Francisco G Tapia. Context-aware deep learning model for yield prediction in potato using time-series uas multispectral data.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18:6096–6115, 2025. 2

    2025

  46. [46]

    Deep gaussian process for crop yield pre- diction based on remote sensing data

    Jiaxuan You, Xiaocheng Li, Melvin Low, David Lobell, and Stefano Ermon. Deep gaussian process for crop yield pre- diction based on remote sensing data. InAAAI conference on artificial intelligence, 2017. 2, 5

    2017

  47. [47]

    Fedformer: Frequency enhanced decom- posed transformer for long-term series forecasting

    Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. Fedformer: Frequency enhanced decom- posed transformer for long-term series forecasting. InIn- ternational Conference on Machine Learning, pages 27268– 27286. PMLR, 2022. 4

    2022