Two peer-reviewed journal articles have recently been published detailing the work undertaken during the EPA-funded Irish Land Mapping Observatory (ILMO) project.
Barrett, B., Nitze., I., Green, S., Cawkwell, F. (2014) Assessment of multi-temporal, multi-sensor radar and ancillary spatial data for grasslands monitoring in Ireland using machine learning approaches. Remote Sensing of Environment, 152 :109-124
Accurate inventories of grasslands are important for studies of carbon dynamics, biodiversity conservation and agricultural management. For regions with persistent cloud cover the use of multi-temporal synthetic aperture radar (SAR) data provides an attractive solution for generating up-to-date inventories of grasslands. This is even more appealing considering the data that will be available from upcoming missions such as Sentinel-1 and ALOS-2. In this study, the performance of three machine learning algorithms; Random Forests (RF), Support Vector Machines (SVM) and the relatively underused Extremely Randomised Trees (ERT) are evaluated for discriminating between grassland types over two large heterogeneous areas of Ireland using multi-temporal, multi-sensor radar and ancillary spatial datasets. A detailed accuracy assessment shows the efficacy of the three algorithms to classify different types of grasslands. Overall accuracies ≥ 88.7% (with kappa coefficient of 0.87) were achieved for the single frequency classifications and maximum accuracies of 97.9% (kappa coefficient of 0.98) for the combined frequency classifications. For most datasets, the ERT classifier outperforms SVM and RF.
Nitze, I., Barrett, B., Cawkwell, F. (2015) Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series. International Journal Of Applied Earth Observation And Geoinformation, 34:136-146.
The analysis and classification of land cover is one of the principal applications in terrestrial remote sensing. Due to the seasonal variability of different vegetation types and land surface characteristics, the ability to discriminate land cover types changes over time. Multi-temporal classification can help to improve the classification accuracies, but different constraints, such as financial restrictions or atmospheric conditions, may impede their application. The optimisation of image acquisition timing and frequencies can help to increase the effectiveness of the classification process. For this purpose, the Feature Importance (FI) measure of the state-of-the art machine learning method Random Forest was used to determine the optimal image acquisition periods for a general (Grassland, Forest, Water, Settlement, Peatland) and Grassland specific (Improved Grassland, Semi-Improved Grassland) land cover classification in central Ireland based on a 9-year time-series of MODIS Terra 16 day composite data (MOD13Q1). Feature Importances for each acquisition period of the Enhanced Vegetation Index (EVI) and Normalised Difference Vegetation Index (NDVI) were calculated for both classification scenarios. In the general land cover classification, the months December and January showed the highest, and July and August the lowest separability for both VIs over the entire nine-year period. This temporal separability was reflected in the classification accuracies, where the optimal choice of image dates outperformed the worst image date by 13% using NDVI and 5% using EVI on a mono-temporal analysis. With the addition of the next best image periods to the data input the classification accuracies converged quickly to their limit at around 8-10 images. The binary classification schemes, using two classes only, showed a stronger seasonal dependency with a higher intra-annual, but lower inter-annual variation. Nonetheless anomalous weather conditions, such as the cold winter of 2009/2010 can alter the temporal separability pattern significantly. Due to the extensive use of the NDVI for land cover discrimination, the findings of this study should be transferrable to data from other optical sensors with a higher spatial resolution. However, the high impact of outliers from the general climatic pattern highlights the limitation of spatial transferability to locations with different climatic and land cover conditions. The use of high-temporal, moderate resolution data such as MODIS in conjunction with machine-learning techniques proved to be a good base for the prediction of image acquisition timing for optimal land cover classification results.