Mapping Miscanthus Using Multi-Temporal Convolutional Neural Network and Google Earth Engine

Xin, Yanan; Adler, Paul R.

doi:10.1145/3356471.3365242

Cited by 6 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, DL techniques that do not rely on expert knowledge are needed so that these identification systems can work over large areas over time. A CNN-LSTM hybrid model was used in [132] to identify grassland types in Sentinel-2 imagery in the United States.…”

Section: Vegetation Mappingmentioning

confidence: 99%

“…Their reported OA is 72% and the authors suggested more seagrass datasets for performance improvement. A CNN-LSTM hybrid model was used in [132] to identify grassland types in Sentinel-2 imagery in the United States. The authors collected ground-truth field data for their experiment, and with the help of GEE for preprocessing and Google Colab for NN training, they received an almost 7% accuracy boost for identifying a type of grass (98.8%, up from 92%).…”

Section: Abbreviationsmentioning

confidence: 99%

See 1 more Smart Citation

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

et al. 2022

View full text Add to dashboard Cite

Remote sensing (RS) plays an important role gathering data in many critical domains (e.g., global climate change, risk assessment and vulnerability reduction of natural hazards, resilience of ecosystems, and urban planning). Retrieving, managing, and analyzing large amounts of RS imagery poses substantial challenges. Google Earth Engine (GEE) provides a scalable, cloud-based, geospatial retrieval and processing platform. GEE also provides access to the vast majority of freely available, public, multi-temporal RS data and offers free cloud-based computational power for geospatial data analysis. Artificial intelligence (AI) methods are a critical enabling technology to automating the interpretation of RS imagery, particularly on object-based domains, so the integration of AI methods into GEE represents a promising path towards operationalizing automated RS-based monitoring programs. In this article, we provide a systematic review of relevant literature to identify recent research that incorporates AI methods in GEE. We then discuss some of the major challenges of integrating GEE and AI and identify several priorities for future research. We developed an interactive web application designed to allow readers to intuitively and dynamically review the publications included in this literature review.

show abstract

Section: Vegetation Mappingmentioning

confidence: 99%

Section: Abbreviationsmentioning

confidence: 99%

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Differentiation of grassy land covers such as native grassland, managed pasture, hay production, and dedicated bioenergy grasses has historically been problematic for RS-based land use mapping (Kline et al, 2013). However, advanced methods show promise for identifying warmseason grasses (Wang et al, 2014(Wang et al, , 2017 and even individual species such as Miscanthus (Xin and Adler, 2019) in cellulosic bioenergy production landscapes. Further refinement of such methods may enable precise, transparent, and low-cost mapping of dedicated energy crop plantings, as well as the previous land uses they replaced.…”

Section: Identifying Ecosystem-atmosphere Exchange With Dedicated Bioenergy Cropsmentioning

confidence: 99%

Revisiting “Additional Carbon”: Tracking Atmosphere–Ecosystem Carbon Exchange to Establish Mitigation and Negative Emissions From Bio-Based Systems

Field

2021

Front. Clim.

View full text Add to dashboard Cite

Climate stabilization plans rely heavily on advanced bioenergy and bioproducts for substitution of fossil-based energy sources and materials, and increasingly, for negative emissions via the direct sequestration of biogenic carbon. Yet, there remain persistent, largely unresolved critiques of bioenergy assessment methodology, particularly in the areas of land use and biogenic carbon accounting. The concept of “additional carbon” calls for evaluating the climate performance of bio-based systems by whether feedstock production creates measurable new local agro-ecosystem uptake of carbon from the atmosphere. This concept is challenging to operationalize for first-generation biofuels, and has largely been advanced as a negative critique. However, carbon additionality is more straightforward to establish—and less critical to overall system mitigation performance—in advanced bioenergy systems. In this Perspective, I review the additional carbon critique, and why it is analytically challenging to address in first-generation biofuel systems based on conventional food crops with large existing markets. Next, I make a case that carbon additionality (1) is more readily achievable with cellulosic feedstocks, (2) is more directly observable for dedicated biomass crops, and (3) is not a strict requirement for achieving net mitigation in carbon-negative bio-based systems. I end by discussing how centering atmosphere–ecosystem carbon exchanges in bio-based system assessment could create new opportunities for enterprise-scale performance monitoring and verification, augmenting and diversifying the current reliance on model-based life-cycle assessment approaches.

show abstract

“…Most of the CNNs analysed demonstrated impressive SRSI classification results, many with an accuracy above 97% [29,32], but almost all were generated using powerful proprietary computers and supercomputers. Some scholars have reviewed the integration of cloud-based systems such as Google Earth Engine (GEE) and Google Collaboratory (GC) to access and classify SRSI using traditional classifiers such as RF [33,34], with some implementing classifications with CNNs [35,36]. GEE is widely used in environmental research because it stores and provides access to many SRSI datasets [32].…”

Section: Introductionmentioning

confidence: 99%

Cloud-Based Monitoring and Evaluation of the Spatial-Temporal Distribution of Southeast Asia’s Mangroves Using Deep Learning

Lomeo

Singh

2022

Remote Sensing

View full text Add to dashboard Cite

This paper proposes a cloud-based mangrove monitoring framework that uses Google Collaboratory and Google Earth Engine to classify mangroves in Southeast Asia (SEA) using satellite remote sensing imagery (SRSI). Three multi-class classification convolutional neural network (CNN) models were generated, showing F1-score values as high as 0.9 in only six epochs of training. Mangrove forests are tropical and subtropical environments that provide essential ecosystem services to local biota and coastal communities and are considered the most efficient vegetative carbon stock globally. Despite their importance, mangrove forest cover continues to decline worldwide, especially in SEA. Scientists have produced monitoring tools based on SRSI and CNNs to identify deforestation hotspots and drive targeted interventions. Nevertheless, although CNNs excel in distinguishing between different landcover types, their greatest limitation remains the need for significant computing power to operate. This may not always be feasible, especially in developing countries. The proposed framework is believed to provide a robust, low-cost, cloud-based, near-real-time monitoring tool that could serve governments, environmental agencies, and researchers, to help map mangroves in SEA.

show abstract

Mapping Miscanthus Using Multi-Temporal Convolutional Neural Network and Google Earth Engine

Cited by 6 publications

References 15 publications

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

Revisiting “Additional Carbon”: Tracking Atmosphere–Ecosystem Carbon Exchange to Establish Mitigation and Negative Emissions From Bio-Based Systems

Cloud-Based Monitoring and Evaluation of the Spatial-Temporal Distribution of Southeast Asia’s Mangroves Using Deep Learning

Contact Info

Product

Resources

About