Boosting Crop Classification by Hierarchically Fusing Satellite, Rotational, and Contextual Data

Accurate in-season crop type classification is crucial for the crop production estimation and monitoring of agricultural parcels. However, the complexity of the plant growth patterns and their spatio-temporal variability present significant challenges. While current deep learning-based methods show promise in crop type classification from single- and multi-modal time series, most existing methods rely on a single modality, such as satellite optical remote sensing data or crop rotation patterns. We propose a novel approach to fuse multimodal information into a model for improved accuracy and robustness across multiple years and countries. The approach relies on three modalities used: remote sensing time series from Sentinel-2 and Landsat 8 observations, parcel crop rotation and local crop distribution. To evaluate our approach, we release a new annotated dataset of 7.4 million agricultural parcels in France and Netherlands. We associate each parcel with time-series of surface reflectance (Red and NIR) and biophysical variables (LAI, FAPAR). Additionally, we propose a new approach to automatically aggregate crop types into a hierarchical class structure for meaningful model evaluation and a novel data-augmentation technique for early-season classification. Performance of the multimodal approach was assessed at different aggregation level in the semantic domain spanning from 151 to 8 crop types or groups. It resulted in accuracy ranging from 91\% to 95\% for NL dataset and from 85\% to 89\% for FR dataset. Pre-training on a dataset improves domain adaptation between countries, allowing for cross-domain zero-shot learning, and robustness of the performances in a few-shot setting from France to Netherlands. Our proposed approach outperforms comparable methods by enabling learning methods to use the often overlooked spatio-temporal context of parcels, resulting in increased preci...

[1]  Daniel Spengler,et al.  Early Crop Classification via Multi-Modal Satellite Data Fusion and Temporal Attention , 2023, Remote. Sens..

[2]  M. Claverie,et al.  Multimodal Crop Type Classification Fusing Multi-Spectral Satellite Time Series with Farmers Crop Rotations and Local Crop Distribution , 2022, CDCEO@IJCAI.

[3]  I. Assent,et al.  Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  David M. Johnson,et al.  Pre- and within-season crop type classification trained with archival land cover information , 2021 .

[5]  Loic Landrieu,et al.  Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series , 2021, Remote. Sens..

[6]  Marco Körner,et al.  EuroCrops: A Pan-European Dataset for Time Series Crop Type Classification , 2021, ArXiv.

[7]  Hannah Kerner,et al.  Learning to predict crop type from heterogeneous sparse labels using meta-learning , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[8]  Michele Meroni,et al.  From parcel to continental scale - A first European crop type map based on Sentinel-1 and LUCAS Copernicus in-situ observations , 2021, Remote Sensing of Environment.

[9]  G. Lemoine,et al.  Comparing land surface phenology of major European crops as derived from SAR and multispectral data of Sentinel-1 and -2 , 2021, Remote sensing of environment.

[10]  R. Hijmans,et al.  The scale dependency of spatial crop species diversity and its relation to temporal diversity , 2020, Proceedings of the National Academy of Sciences.

[11]  Koutilya PNVR,et al.  Pre-season crop type mapping using deep neural networks , 2020, Comput. Electron. Agric..

[12]  Iryna Gurevych,et al.  AdapterHub: A Framework for Adapting Transformers , 2020, EMNLP.

[13]  Nesrine Chehata,et al.  Improved Crop Classification with Rotation Knowledge using Sentinel-1 and -2 Time Series , 2020 .

[14]  Marc Rußwurm,et al.  Meta-Learning for Few-Shot Land Cover Classification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[15]  Andrej Ceglar,et al.  Detecting flowering phenology in oil seed rape parcels with Sentinel-1 and -2 time series , 2020, Remote sensing of environment.

[16]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[17]  Nesrine Chehata,et al.  Satellite Image Time Series Classification With Pixel-Set Encoders and Temporal Self-Attention , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Marc Rußwurm,et al.  Self-Attention for Raw Optical Satellite Time Series Classification , 2019, ArXiv.

[19]  Marc Rußwurm,et al.  BreizhCrops: A Satellite Time Series Dataset for Crop Type Identification , 2019, ArXiv.

[20]  N. Courty,et al.  End-to-end learned early classification of time series for in-season crop type mapping , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[21]  Nesrine Chehata,et al.  Time-Space Tradeoff in Deep Learning Models for Crop Classification on Satellite Multi-Spectral Image Time Series , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[22]  C. Justice,et al.  The Harmonized Landsat and Sentinel-2 surface reflectance data set , 2018, Remote Sensing of Environment.

[23]  Geoffrey I. Webb,et al.  Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series , 2018, Remote. Sens..

[24]  Thomas Wolf,et al.  A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks , 2018, AAAI.

[25]  Pierre Defourny,et al.  Retrieval of the canopy chlorophyll content from Sentinel-2 spectral bands to estimate nitrogen uptake in intensive winter wheat cropping systems , 2018, Remote Sensing of Environment.

[26]  Jing Huang,et al.  DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[27]  Chloé Clavel,et al.  Attitude Classification in Adjacency Pairs of a Human-Agent Interaction with Hidden Conditional Random Fields , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[28]  Pierre Soille,et al.  A versatile data-intensive computing platform for information retrieval from big geospatial data , 2018, Future Gener. Comput. Syst..

[29]  Marc Rußwurm,et al.  Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders , 2018, ISPRS Int. J. Geo Inf..

[30]  Sen Wang,et al.  Multimodal sentiment analysis with word-level fusion and reinforcement learning , 2017, ICMI.

[31]  Valentin Barrière,et al.  Hybrid models for opinion analysis in speech interactions , 2017, ICMI.

[32]  S. Essid,et al.  Opinion Dynamics Modeling for Movie Review Transcripts Classification with Hidden Conditional Random Fields , 2017, INTERSPEECH.

[33]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[34]  Rogerio Bonifacio,et al.  Automatic smoothing of remote sensing data , 2017, 2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp).

[35]  Maite Taboada,et al.  Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications , 2017, CL.

[36]  Fabio A. González,et al.  Gated Multimodal Units for Information Fusion , 2017, ICLR.

[37]  Eduardo Coutinho,et al.  The INTERSPEECH 2016 Computational Paralinguistics Challenge: Deception, Sincerity & Native Language , 2016, INTERSPEECH.

[38]  George Trigeorgis,et al.  Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[39]  Yoshua Bengio,et al.  End-to-end attention-based large vocabulary speech recognition , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[40]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[41]  Jordi Inglada,et al.  Assessment of a Markov logic model of crop rotations for early crop mapping , 2015, Comput. Electron. Agric..

[42]  Yoshua Bengio,et al.  Gated Feedback Recurrent Neural Networks , 2015, ICML.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[44]  M. Benoît,et al.  Modeling the spatial distribution of crop sequences at a large regional scale using land-cover survey data: A case from France , 2014 .

[45]  M. Claverie,et al.  Validation of coarse spatial resolution LAI and FAPAR time series over cropland in southwest France , 2013 .

[46]  Dacheng Tao,et al.  A Survey on Multi-view Learning , 2013, ArXiv.

[47]  M. K. van Ittersum,et al.  ROTAT, a tool for systematically generating crop rotations , 2003 .

[48]  F. Baret,et al.  Evaluation of Canopy Biophysical Variable Retrieval Performances from the Accumulation of Large Swath Satellite Data , 1999 .

[49]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[50]  Gabriel Tseng CropHarvest: a global satellite dataset for crop type classification , 2021 .

[51]  M. Weiss,et al.  Remote sensing for agricultural applications: A meta-review , 2020 .

[52]  D. Lobell,et al.  Food security and food production systems , 2017 .

[53]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[54]  Zellig S. Harris,et al.  Distributional Structure , 1954 .