Crop Classification using Multi-spectral and Multitemporal Satellite Imagery with Machine Learning

Viskovic, Lucija; Kosović, Ivana Nižetić; Mastelić, Toni

doi:10.23919/softcom.2019.8903738

Cited by 18 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Generally, there is a tradeoff between temporal and spatial resolution, for example the National Agriculture Imagery Program (NAIP) acquires data with 1 meter resolution, but on a 3-year cycle [4]. For large-scale classification problems, temporal resolution becomes of utmost importance [29], especially since stochastic cloud cover can render any given satellite capture unusable. Moreover, transformer architectures have shown their efficacy on temporal satellite data [25].…”

Section: Machine Learning On Satellite Datamentioning

confidence: 99%

Activation Regression for Continuous Domain Generalization with Applications to Crop Classification

Samar¹,

Wallace²,

Bala³

et al. 2022

Preprint

View full text Add to dashboard Cite

Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. In this paper, we model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem, demonstrating how models generalise better with appropriate domain knowledge. We develop a dataset spatially distributed across the entire continental United States, providing macroscopic insight into the effects of geography on crop classification in multi-spectral and temporally distributed satellite imagery. Our method demonstrates improved generalisability from 1) passing geographically correlated climate variables along with the satellite data to a Transformer model and 2) regressing on the model features to reconstruct these domain variables. Combined, we provide a novel perspective on geographic generalisation in satellite imagery and a simple-yet-effective approach to leverage domain knowledge. Code is available at: https://github.com/ samar-khanna/cropmap

show abstract

Section: Machine Learning On Satellite Datamentioning

confidence: 99%

Activation Regression for Continuous Domain Generalization with Applications to Crop Classification

Samar¹,

Wallace²,

Bala³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Модель показала высокую меру точности классификации F-мера 88,7 %, сравнимую, а по нескольким классам превосходящую, точность для схожих моделей других авторов [Viskovic, 2019;. Наибольшая точность была достигнута для наиболее широко представленных классов: пшеницы, сои и подсолнечника.…”

Section: анализ результатовunclassified

Технология Интеллектуального Распознавания Сельскохозяйственных Культур Нейронной Сетью По Мультиспектральным Многовременным Данным Дистанционного Зондирования Земли

Асадуллаев¹,

Кузьменко²

2022

ЭИ

View full text Add to dashboard Cite

В данной работе представлена технология распознавания сельскохозяйственных культур по данным дистанционного зондирования Земли. Апробация технологии была проведена на сельскохозяйственных землях Белгородской области Российской Федерации. В соответствии со статистикой севооборота были выбраны следующие сельскохозяйственные культуры: пшеница, ячмень, кукуруза, подсолнечник, соя, сахарная свекла, многолетние травы и пары. В качестве входных данных были использованы мультиспектральные снимки со спутника Sentinel-2 уровня обработки MSI L2A, а именно каналы RGB-спектра, SWIR и NIR. Из полученных данных были составлены временные ряды в вегетационные периоды за 2018–2020 годы. Разработан алгоритм устранения пропусков данных в дни высокой облачности для повышения качества распознавания. В качестве модели классификатора была использована сверточно-рекуррентная нейронная сеть. Разработанная модель на тестовых данных показала общую меру точности f-мера 88,7 %. Предложенная архитектура нейронной сети также применима в других регионах со схожей посевной структурой, фенологическими показателями культур и схожими климатическими условиями.

show abstract

“…According to the authors, although the use of S1 imagery affected the LCC, their ability to classify crop type was weaker than for S2 data. Viskovic et al (2019) used MT S1 and S2 data for crop classification. RF outperformed other classifiers (e.g., SVM, K-nearest neighbors) with an OA of 84.20%, and Kappa 0.82.…”

Section: Land-cover Classification On a Multitemporal S1 And S2 Imagerymentioning

confidence: 99%

Integration of Multitemporal Sentinel-1 and Sentinel-2 Imagery for Land-Cover Classification Using Machine Learning Methods

Dobrinić

Medak

Gašparović

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Using space-borne remote sensing data is widely used for land-cover classification (LCC) due to its ability to provide a big amount of data with a regular temporal revisit time. In recent years, optical and synthetic aperture radar (SAR) imagery have become available for free, and their integration in time series have improved LCC. This research evaluates the classification accuracy using multitemporal (MT) Sentinel-1 (S1) and Sentinel-2 (S2) imagery. Pixel-based LCC is made for S1 and S2 imagery, and for a combination of both datasets with Random Forest (RF) and Extreme Gradient Boosting (XGBoost; XGB). The extent of the study area, is located in the south-east of France, in Lyon. Regardless of LCC using single-date or MT data, the highest classification results were achieved with integrated S1 and S2 imagery and XGB method, whereas overall accuracy (OA) and Kappa coefficient (Kappa) increased from 85.51% to 91.09%, and from 0.81 to 0.88, respectively. Furthermore, the integration of MT imagery significantly improved the classification of urban areas and reduced misclassification between forest and low vegetation. In this paper, in terms of the pixel-based classification, XGB produced slightly better results than RF, and outperformed it in terms of computational time. This research improved LCC with integration of radar and optical MT imagery, which can be useful for areas hampered by a frequent cloud cover. Future work should use the aforementioned data for specific applications in remote sensing, as well as evaluate the classification performance with different approaches, such as neural networks or deep learning.

show abstract

Crop Classification using Multi-spectral and Multitemporal Satellite Imagery with Machine Learning

Cited by 18 publications

References 13 publications

Activation Regression for Continuous Domain Generalization with Applications to Crop Classification

Activation Regression for Continuous Domain Generalization with Applications to Crop Classification

Integration of Multitemporal Sentinel-1 and Sentinel-2 Imagery for Land-Cover Classification Using Machine Learning Methods

Contact Info

Product

Resources

About