Abstract

The size and location of agricultural fields that are in active use and the type of use during the growing season are among the vital information that is needed for the careful planning and forecasting of agricultural production at national and regional scales. In areas where such data are not readily available, an independent seasonal monitoring method is needed. Remote sensing is a widely used tool to map land use types, although there are some limitations that can partly be circumvented by using, among others, multiple observations, careful feature selection and appropriate analysis methods. Here, we used Sentinel-2 satellite image time series (SITS) over the land area of Norway to map three agricultural land use classes: cereal crops, fodder crops (grass) and unused areas. The Multilayer Perceptron (MLP) and two variants of the Convolutional Neural Network (CNN), are implemented on SITS data of four different temporal resolutions. These enabled us to compare twelve model-dataset combinations to identify the model-dataset combination that results in the most accurate predictions. The CNN is implemented in the spectral and temporal dimensions instead of the conventional spatial dimension. Rather than using existing deep learning architectures, an autotuning procedure is implemented so that the model hyperparameters are empirically optimized during the training. The results obtained on held-out test data show that up to 94% overall accuracy and 90% Cohen’s Kappa can be obtained when the 2D CNN is applied on the SITS data with a temporal resolution of 7 days. This is closely followed by the 1D CNN on the same dataset. However, the latter performs better than the former in predicting data outside the training set. It is further observed that cereal is predicted with the highest accuracy, followed by grass. Predicting the unused areas has been found to be difficult as there is no distinct surface condition that is common for all unused areas.

Highlights

  • There is a consensus that modern agricultural production is expected to happen within the requirements of sustainability and climate change [1,2]

  • This paper presents an application of deep learning algorithms and satellite image time series (SITS) data from Sentinel-2 to map and monitor agricultural land use in Norway

  • Four major results are presented in the above section: namely, temporal signatures of the three different seasonal land use classes, the architectures of the optimized models of the twelve model–dataset combinations, the accuracies of the model

Read more

Summary

Introduction

There is a consensus that modern agricultural production is expected to happen within the requirements of sustainability and climate change [1,2]. This demands careful planning and precise forecasting of agricultural production, which rely on up-to-date, detailed and accurate information about agricultural land use [3,4]. Important is the size and location of agricultural fields that are unused during a growing season. These areas are either temporarily or permanently out of food and fodder production. According to national agricultural policy in Norway, it is a goal to increase food production by 20 percent within

Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call