Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series

Quinton, Félix; Landrieu, Loïc

doi:10.3390/rs13224599

Cited by 7 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the authors utilized self-organizing Kohonen maps (SOMs) to reconstruct missing data due to cloudy holes. [25] 2020 LSTM, MLP, U-net Sentinel-1, Sentinel-2 ( 14) [32] 2021 ANN Sentinel-2 (4) [33] 2021 PSE + LTAE Sentinel-2 (20) [34] 2021 Bi-LSTM, LSTM Sentinel-2 ( 16) [35] 2021 CNN Sentinel-2 (11) [36] 2021 CNN-CRF, CNN Sentinel-1 (9) [37] 2021 MSFCN, CNN, Sentinel-1 ( 14) [38] 2021 LSTM, CNN, GAN Landsat-8 (3) [39] 2021 CNN AgriSAR (6) [40] 2022 CNN Sentinel2-Agri ( 20)…”

Section: Crop Classification Using Satellite Datamentioning

confidence: 99%

“…The technique was put into practice in a study region in Spain to manage subsidies under the European Union (EU) Common Agricultural Policy (CAP). In the study described in [33], a framework is presented that models crop rotation explicitly, both at the intra-annual and inter-annual scales, using a combination of Pixel Set Encoder (PSE) and Lightweight Temporal Attention Encoder (LTAE) to process Sentinel-2 satellite data. The PSE + LTAE network is also modified to model crop rotation.…”

Section: Crop Classification Using Satellite Datamentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review

et al. 2023

View full text Add to dashboard Cite

In recent years, the use of remote sensing data obtained from satellite or unmanned aerial vehicle (UAV) imagery has grown in popularity for crop classification tasks such as yield prediction, soil classification or crop mapping. The ready availability of information, with improved temporal, radiometric, and spatial resolution, has resulted in the accumulation of vast amounts of data. Meeting the demands of analysing this data requires innovative solutions, and artificial intelligence techniques offer the necessary support. This systematic review aims to evaluate the effectiveness of deep learning techniques for crop classification using remote sensing data from aerial imagery. The reviewed papers focus on a variety of deep learning architectures, including convolutional neural networks (CNNs), long short-term memory networks, transformers, and hybrid CNN-recurrent neural network models, and incorporate techniques such as data augmentation, transfer learning, and multimodal fusion to improve model performance. The review analyses the use of these techniques to boost crop classification accuracy by developing new deep learning architectures or by combining various types of remote sensing data. Additionally, it assesses the impact of factors like spatial and spectral resolution, image annotation, and sample quality on crop classification. Ensembling models or integrating multiple data sources tends to enhance the classification accuracy of deep learning models. Satellite imagery is the most commonly used data source due to its accessibility and typically free availability. The study highlights the requirement for large amounts of training data and the incorporation of non-crop classes to enhance accuracy and provide valuable insights into the current state of deep learning models and datasets for crop classification tasks.

show abstract

Section: Crop Classification Using Satellite Datamentioning

confidence: 99%

Section: Crop Classification Using Satellite Datamentioning

confidence: 99%

Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Penelitian lain juga dilakukan oleh (Ofori-Ampofo dkk., 2021) yang membuat peta jenis tanaman di wilayah Finistère, Brittany Barat, Prancis. Penerapan klasifikasi SITS dengan deep learning juga diterapkan untuk pemodelan rotasi tanaman di wilayah tenggara Prancis (Quinton & Landrieu, 2021).…”

Section: Pendahuluanunclassified

Klasifikasi Penginderaan Jauh Berbasis Time Series Menggunakan Multi-Layer Perceptron (MLP) Untuk Pemetaan Jenis Tanaman (Studi Kasus: Desa Girimulyo, Lampung Timur)

Rohman,

Fauzi,

Swastika

et al. 2023

J. Geosains Remote Sens.

View full text Add to dashboard Cite

Penerapan metode klasifikasi time series penginderaan jauh dengan deep learning merupakan metode inovatif yang mampu mengekstrak informasi penting dari banyaknya data observasi bumi yang beragam dengan cepat dan akurat. Penelitian ini menyajikan metode klasifikasi berbasis time series menggunakan Multi-Layer Perceptron (MLP) untuk pemetaan jenis tanaman sebagai upaya untuk mendukung ketahanan pangan dengan menyediakan produk tutupan lahan berupa peta jenis tanaman. Penelitian ini menggunakan data citra Sentinel-2A dan 150 sampel berupa koordinat titik dari lima kelas yang disimpan dalam bentuk data cube teregulerisasi sebagai dasar informasi untuk pembentukan model klasifikasi menggunakan MLP. Berdasarkan hasil penelitian, jenis tanaman pada Desa Girimulyo diklasifikasikan ke dalam lima kelas klasifikasi yakni kelas jagung dengan luas 22,2 km2, kelas tanaman lain dengan luas 9,9 km2, kelas pisang dengan luas 6,3 km2, kelas kelapa dengan luas 3,7 km2, dan kelas non-tanaman dengan luas 2,8 km2. Hasil penelitian ini menunjukkan bahwa metode klasifikasi yang digunakan efektif untuk memetakan jenis tanaman di wilayah studi dibuktikan dengan nilai overall accuracy dari citra terklasifikasi yang mencapai 83%. Penelitian selanjutnya diharapkan dapat dilakukan dengan jumlah sampel yang lebih banyak pada wilayah studi dengan jenis tanaman yang lebih beragam.

show abstract

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Nguyen,

Rußwurm,

Lenczner

et al. 2024

Remote Sensing of Environment

View full text Add to dashboard Cite

Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series

Cited by 7 publications

References 29 publications

Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review

Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review

Klasifikasi Penginderaan Jauh Berbasis Time Series Menggunakan Multi-Layer Perceptron (MLP) Untuk Pemetaan Jenis Tanaman (Studi Kasus: Desa Girimulyo, Lampung Timur)

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Contact Info

Product

Resources

About