IP Library Granted Patent US 12,731,196
Granted Patent B2
US 12,731,196 · App. 18/374,568 · Granted Sep 8, 2026

Fusing multimodal environmental data for agricultural inference

Inventors: Yawen Zhang (Mountain View, CA); Kezhen Chen (San Mateo, CA); Jinmeng Rao (Sunnyvale, CA); Xiaoyuan Guo (Palo Alto, CA); Jie Yang (Sunnyvale, CA); Luis Pazos Outon (Mountain View, CA)
Assignee: Deere & Company
G06Q50/16A01B79/005G06Q50/02G06V20/188
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,731,196
App. No.
18/374,568
Granted
Sep 8, 2026
Kind
B2
Abstract

Implementations are disclosed for fusing multiple modalities of data into a multimodal feature embedding and then processing the multimodal feature embedding using various downstream processes for training and/or inference purposes. In various implementations, multiple different modalities of agricultural data about an agricultural parcel may be obtained. Each modality of agricultural data may be processed based on a respective modality-specific encoder to generate a respective modality-specific embedding. The plurality of modality-specific embeddings may be processed based on a multimodal fusion machine learning model to generate a multimodal feature embedding that represents the agricultural parcel. In some implementations, the multimodal feature embedding may be processed using downstream computer process(es) to generate agricultural prediction(s) about the agricultural parcel. Additionally or alternatively, the multimodal feature embedding may be used to train the multimodal fusion model and/or the modality specific encoder(s).

Claims (40)

1 . A method implemented using one or more processors, comprising:

obtaining multiple different modalities of agricultural data about an agricultural parcel corresponding to a first time;

processing a first modality of agricultural data based on a first modality-specific encoder to generate a first modality-specific embedding and a second modality of agricultural data based on a second modality-specific encoder to generate a second modality-specific embedding, wherein the first and second modality-specific encoders are pre-trained for the first and second modalities of agricultural data, respectively, using masked autoencoding;

processing a plurality of the modality-specific embeddings based on a multimodal fusion machine learning model to generate a multimodal feature embedding that represents the agricultural parcel, the plurality of the modality-specific embeddings including the first modality-specific embedding and the second modality-specific embedding;

generating a third modality of agricultural data using the multimodal feature embedding, the third modality of agricultural data different than the multiple different modalities of agricultural data;

generating, using one or more downstream computer processes, one or more agricultural predictions about the agricultural parcel based on the multimodal feature embedding, the one or more agricultural predictions to include agricultural data corresponding to a second time, the second time different than the first time; and

causing one or more computing devices to render output that includes one or more of the agricultural predictions.

2 . The method of claim 1 , wherein the multimodal fusion machine learning model is jointly trained with at least some of the first or second modality-specific encoders.

3 . The method of claim 2 , wherein the multimodal fusion machine learning model is jointly trained using the masked autoencoding.

4 . The method of claim 1 , wherein the multimodal fusion machine learning model includes a transformer.

5 . The method of claim 1 , wherein the multiple different modalities of data include at least one modality that includes agricultural time series data about the agricultural parcel.

6 . The method of claim 5 , wherein the agricultural time series data about the agricultural parcel includes soil moisture data.

7 . The method of claim 5 , wherein the agricultural time series data about the agricultural parcel includes climate data.

8 . The method of claim 1 , wherein the multiple different modalities of data include at least one modality that includes tabular data about the agricultural parcel.

9 . The method of claim 8 , wherein the tabular data includes soil properties of the agricultural parcel.

10 . The method of claim 1 , wherein the multiple different modalities of data include at least one modality that includes satellite or aerial imagery of the agricultural parcel.

11 . The method of claim 1 , wherein one or more of the downstream computer processes includes identifying one or more reference multimodal feature embeddings that are sufficiently proximate to the multimodal feature embedding in an embedding space, wherein the one or more reference multimodal feature embeddings were generated by processing the multiple different modalities of agricultural data about one or more reference agricultural parcels.

12 . The method of claim 11 , wherein the output includes a recommendation of a suitable crop for the agricultural parcel, wherein the suitable crop is selected based on having been grown in the one or more reference agricultural parcels.

13 . The method of claim 1 , wherein one or more of the downstream computer processes includes processing the multimodal feature embedding using a downstream machine learning model to perform multi-crop yield forecasting for the agricultural parcel.

14 . A system comprising one or more processors and memory storing instructions that, in response to execution by the one or more processors, cause the one or more processors to:

obtain multiple different modalities of agricultural data about an agricultural parcel corresponding to a first time;

process a first modality of agricultural data based on a first modality-specific encoder to generate a first modality-specific embedding and a second modality of agricultural data based on a second modality-specific encoder to generate a second modality-specific embedding, wherein the first and second modality-specific encoders are pre-trained for the first and second modalities of agricultural data, respectively, using masked autoencoding;

process a plurality of the modality-specific embeddings based on a multimodal fusion machine learning model to generate a multimodal feature embedding that represents the agricultural parcel, the plurality of the modality-specific embeddings including the first modality-specific embedding and the second modality-specific embedding;

generate a third modality of agricultural data using the multimodal feature embedding, the third modality of agricultural data different than the multiple different modalities of agricultural data;

generate, using one or more downstream computer processes, one or more agricultural predictions about the agricultural parcel based on the multimodal feature embedding, the one or more agricultural predictions to include agricultural data corresponding to a second time, the second time different than the first time; and

cause one or more computing devices to render output that includes one or more of the agricultural predictions.

15 . The system of claim 14 , wherein the multimodal fusion machine learning model is jointly trained with at least some of the first or second modality-specific encoders.

16 . The system of claim 15 , wherein the multimodal fusion machine learning model is jointly trained using the masked autoencoding.

17 . The system of claim 14 , wherein the multimodal fusion machine learning model includes a transformer.

18 . The system of claim 14 , wherein the multiple different modalities of data include at least one modality that includes agricultural time series data about the agricultural parcel.

19 . A method implemented using one or more processors, comprising:

obtaining multiple different modalities of agricultural data about an agricultural parcel corresponding to a first time;

masking one or more of the multiple different modalities of agricultural data;

processing a remaining first modality of agricultural data based on a first modality-specific encoder to generate a first modality-specific embedding and a remaining second modality of agricultural data based on a second modality-specific encoder to generate a second modality-specific embedding, wherein the first and second modality-specific encoders are pre-trained for the remaining first and second modalities of agricultural data, respectively, using masked autoencoding;

processing a plurality of the modality-specific embeddings based on a multimodal fusion machine learning model to generate a multimodal feature embedding that represents the agricultural parcel, the plurality of the modality-specific embeddings including the first modality-specific embedding and the second modality-specific embedding;

generating a third modality of agricultural data using the multimodal feature embedding, the third modality of agricultural data different than the multiple different modalities of agricultural data;

generating, using one or more downstream computer processes, one or more agricultural predictions about the agricultural parcel based on the multimodal feature embedding, the one or more agricultural predictions to include agricultural data corresponding to a second time, the second time different than the first time;

comparing the one or more agricultural predictions to one or more ground truth observations; and

training the multimodal fusion machine learning model based on the comparing.

20 . The method of claim 19 , further including jointly training one or more of the first or second modality-specific encoders based on the comparing.

Assignments (2)
MERGER Recorded Jun 26, 2024
From: MINERAL EARTH SCIENCES LLC
To: DEERE & CO.
Reel/Frame 068055/0420 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 18, 2023
From: ZHANG, YAWEN; CHEN, KEZHEN; RAO, JINMENG; GUO, XIAOYUAN; YANG, JIE; OUTON, LUIS PAZOS
To: MINERAL EARTH SCIENCES LLC
Reel/Frame 065270/0178 →
Continuity (1)
Related Publication 20250148555A1 · May 8, 2025
References Cited (31)
US 11321347B1 · Clifford · 2022 [cited by examiner]
US 11406097B2 · Sibley et al. · 2022 [cited by applicant]
US 20200126232A1 · Guo · 2020 [cited by examiner]
US 20210118097A1 · Guan et al. · 2021 [cited by applicant]
US 20220061236A1 · Guan et al. · 2022 [cited by applicant]
US 20220343194A1 · Louisell, III · 2022 [cited by examiner]
US 20230091677A1 · Brown · 2023 [cited by examiner]
US 20230165181A1 · Scheiner · 2023 [cited by examiner]
US 20240144424A1 · Ma · 2024 [cited by examiner]
US 20240203119A1 · Ma · 2024 [cited by examiner]
US 20240212068A1 · Qian · 2024 [cited by examiner]
AWS, What are Embeddings in Machine Learning?, accessed Aug. 5, 2025 (Year: 2025). [cited by examiner]
Geeks for Geeks, What are Embedding in Machine Learning?, accessed Aug. 5, 2025 (Year: 2025). [cited by examiner]
Fuller, et al., Transfer learning with pretrained remote sensing transformers, arXiv preprint arXiv:2209.14969, 2022 (Year: 2022). [cited by examiner]
Moumni, et al., Machine learning-based classification for crop-type mapping using the fusion of high-resolution satellite imagery in a semiarid area, Scientifica vol. 2021, No. 1, 2021, 8810279 (Year: 2021). [cited by examiner]
Shen, et al., Missing data imputation for solar yield prediction using temporal multi-modal variational auto-encoder, Proceedings of the 29th ACM international conference on multimedia, 2021 (Year: 2021). [cited by examiner]
Chlingaryan, et al., Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review, Computers and Electronics in Agriculture, vol. 151, 2018, pp. 61-69 (Year: 20… [cited by examiner]
Andreadis, Missing values imputation on multivariate time series in the field of agriculture, Fac. Sci., School Inform., Aristotle Univ. Thessaloniki, Thessaloniki, Greece, 2022 (Year: 2022). [cited by examiner]
Zhao, et al., Evaluation of five deep learning models for crop type mapping using sentinel-2 time series images with missing information, Remote Sensing, vol. 13, No. 14, 2021, 2790 (Year: 2021). [cited by examiner]
Zheng, et al., Deep multisensor learning for missing-modality all-weather mapping, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 174, 2021, pp. 254-264 (Year: 2021). [cited by examiner]
Wang, Deep Neural Networks and Transfer Learning for Crop Phenotyping Using Multi-Modality Remote Sensing and Environmental Data, Diss. Purdue University, May 2023 (Year: 2023). [cited by examiner]
He et al., “Masked Autoencoders Are Scalable Vision Learners” arXiv:2111.06377v3 [cs.CV], 14 pages, dated Dec. 19, 2021. [cited by applicant]
Ouhami et al., “Computer Vision, IoT and Data Fusion for Crop Disease Detection Using Machine Learning: A Survey and Ongoing Research” Remote Sens. 2021, 13, 2486. Retrieved from https://doi.org/10.3390/rs13132486. [cited by applicant]
Jayme Garcia Arnal Barbedo “Data Fusion in Agriculture: Resolving Ambiguities and Closing Data Gaps” Sensors 2022, 22, 2285. Retrieved from https://doi.org/10.3390/s22062285. 20 pages. [cited by applicant]
Yuxing Chen et al., Incomplete Multimodal Learning for Remote Sensing Data Fusion, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, pp. 1-13, Apr. 22, 2023, XP091491336. [cited by applicant]
Chaoning Zhang et al., A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, pp. 1-13, Jul. 30, 2022, XP09128… [cited by applicant]
Fudong Lin et al., MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, Sep. 16, 202… [cited by applicant]
Extended European Search Report and Written Opinion issued in European Patent Application No. 24203384.3 dated Mar. 5, 2025, in 09 pages. [cited by applicant]
Wang et al., “Prototype-based Selective Knowledge Distillation for Zero-Shot Sketch Based Image Retrieval,” MM '22: Proceedings of the 30th ACM International Conference on Multimedia, Oct. 10, 2022, pp. 601-609, retriev… [cited by applicant]
Song et al., “Image Matching and Localization Based on Fusion of Handcrafted and Deep Features,” IEEE Sensors Journal, vol. 23, No. 19, Oct. 1, 2023, pp. 22967-22983, retrieved from <doi.org/10.1109/JSEN.2023.3305677> o… [cited by applicant]
European Patent Office, “Communication Pursuant to Article 94(3) EPC,” issued in connection with European Patent Application No. 24203384.3 dated Jun. 18, 2026, 32 pages. [cited by applicant]