Scientific publications

@article{nokey,

title = {A Downsampling Method Addressing the Modifiable Areal Unit Problem in Remote Sensing},

author = {Andrei Mîrț and Johannes Reiche and Jan Verbesselt and Martin Herold},

url = {https://www.mdpi.com/2072-4292/14/21/5538},

doi = {https://doi.org/10.3390/rs14215538},

year  = {2022},

date = {2022-11-03},

journal = {Remote Sensing},

volume = {14},

number = {5538},

issue = {22},

abstract = {Handling multiple scales efficiently is one avenue for processing big remote sensing imagery data. Unfortunately, imagery is also affected by the infamous modifiable areal unit problem, which creates unpredictable errors at different scales. We developed a downsampling method that attempts to keep the data distribution in a downsampled image constant, reducing the modifiable areal unit problem. We tested our method against classic downsampling methods (mean, central pixel selection, random) under a range of typical remote sensing scenarios. Under our experimental conditions, our downsampling method consistently outperformed the classical downsampling methods within a 95% confidence level. The downsampling method can be used in most typical situations where downsampling is needed, but it is likely to shine when used as a pyramid building policy in geocomputing platforms, such as Google Earth Engine.},

keywords = {big data, downsampling, modifiable areal unit problem, multscale, remote sensing},

pubstate = {published},

tppubtype = {article}

}

@article{@article{doi:10.1080/15481603.2022.2115619,

title = {Using high-resolution imagery and deep learning to classify land-use following deforestation: a case study in Ethiopia},

author = {Robert N. Masolele and Veronique De Sy and Diego Marcos and Jan Verbesselt and Fabian Gieseke and Kalkidan Ayele Mulatu and Yitebitu Moges and Heiru Sebrala and Christopher Martius and Martin Herold},

url = {https://doi.org/10.1080/15481603.2022.2115619

},

doi = {https://doi.org/10.1080/15481603.2022.2115619},

year  = {2022},

date = {2022-09-07},

urldate = {2022-09-07},

journal = {GIScience & Remote Sensing},

volume = {59},

number = {1},

pages = {1446-1472},

abstract = {National-scale assessments of post-deforestation land-use are crucial for decreasing deforestation and forest degradation-related emissions. In this research, we assess the potential of different satellite data modalities (single-date, multi-date, multi-resolution, and an ensemble of multi-sensor images) for classifying land-use following deforestation in Ethiopia using the U-Net deep neural network architecture enhanced with attention. We performed the analysis on satellite image data retrieved across Ethiopia from freely available Landsat-8, Sentinel-2 and Planet-NICFI satellite data. The experiments aimed at an analysis of (a) single-date images from individual sensors to account for the differences in spatial resolution between image sensors in detecting land-uses, (b) ensembles of multiple images from different sensors (Planet-NICFI/Sentinel-2/Landsat-8) with different spatial resolutions, (c) the use of multi-date data to account for the contribution of temporal information in detecting land-uses, and, finally, (d) the identification of regional differences in terms of land-use following deforestation in Ethiopia. We hypothesize that choosing the right satellite imagery (sensor) type is crucial for the task. Based on a comprehensive visually interpreted reference dataset of 11 types of post-deforestation land-uses, we find that either detailed spatial patterns (single-date Planet-NICFI) or detailed temporal patterns (multi-date Sentinel-2, Landsat-8) are required for identifying land-use following deforestation, while medium-resolution single-date imagery is not sufficient to achieve high classification accuracy. We also find that adding soft-attention to the standard U-Net improved the classification accuracy, especially for small-scale land-uses. The models and products presented in this work can be used as a powerful data resource for governmental and forest monitoring agencies to design and monitor deforestation mitigation measures and data-driven land-use policy.},

keywords = {Attention U-Net, deep learning, deforestation drivers, Planet-NFCI, remote sensing},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Paddy rice methane emissions across Monsoon Asia},

author = {Zutao Ouyang and Robert B. Jackson and Gavin McNicol and Etienne Fluet-Chouinard and Benjamin R.K. Runkle and Dario Papale and Sara H. Knox and Sarah Cooley and Kyle B. Delwiche and Sarah Feron and Jeremy Andrew Irvin and Avni Malhotra and Muhammad Muddasir and Simone Sabbatini and Ma. Carmelita R. Alberto and Alessandro Cescatti and Chi-Ling Chen and Jinwei Dong and Bryant N. Fong and Haiqiang Guo and Lu Hao and Hiroki Iwata and Qingyu Jia and Weimin Ju and Minseok Kang and Hong Li and Joon Kim and Michele L. Reba and Amaresh Kumar Nayak and Debora Regina Roberti and Youngryel Ryu and Chinmaya Kumar Swain and Benjei Tsuang and Xiangming Xiao and Wenping Yuan and Geli Zhang and Yongguang Zhang},

url = {https://www.sciencedirect.com/science/article/pii/S0034425722004412},

doi = {https://doi.org/10.1016/j.rse.2022.113335},

issn = {0034-4257},

journal = {Remote Sensing of Environment},

volume = {284},

pages = {113335},

abstract = {Although rice cultivation is one of the most important agricultural sources of methane (CH4) and contributes ∼8% of total global anthropogenic emissions, large discrepancies remain among estimates of global CH4 emissions from rice cultivation (ranging from 18 to 115 Tg CH4 yr−1) due to a lack of observational constraints. The spatial distribution of paddy-rice emissions has been assessed at regional-to-global scales by bottom-up inventories and land surface models over coarse spatial resolution (e.g., > 0.5°) or spatial units (e.g., agro-ecological zones). However, high-resolution CH4 flux estimates capable of capturing the effects of local climate and management practices on emissions, as well as replicating in situ data, remain challenging to produce because of the scarcity of high-resolution maps of paddy-rice and insufficient understanding of CH4 predictors. Here, we combine paddy-rice methane-flux data from 23 global eddy covariance sites and MODIS remote sensing data with machine learning to 1) evaluate data-driven model performance and variable importance for predicting rice CH4 fluxes; and 2) produce gridded up-scaling estimates of rice CH4 emissions at 5000-m resolution across Monsoon Asia, where ∼87% of global rice area is cultivated and ∼ 90% of global rice production occurs. Our random-forest model achieved Nash-Sutcliffe Efficiency values of 0.59 and 0.69 for 8-day CH4 fluxes and site mean CH4 fluxes respectively, with land surface temperature, biomass and water-availability-related indices as the most important predictors. We estimate the average annual (winter fallow season excluded) paddy rice CH4 emissions throughout Monsoon Asia to be 20.6 ± 1.1 Tg yr−1 for 2001–2015, which is at the lower range of previous inventory-based estimates (20–32 CH4 Tg yr−1). Our estimates also suggest that CH4 emissions from paddy rice in this region have been declining from 2007 through 2015 following declines in both paddy-rice growing area and emission rates per unit area, suggesting that CH4 emissions from paddy rice in Monsoon Asia have likely not contributed to the renewed growth of atmospheric CH4 in recent years.},

keywords = {climate change, machine learning, remote sensing},

pubstate = {published},

tppubtype = {article}

}