Machine learning versus deep learning in land system science: a decision-making framework for effective land classification

Jane Southworth; Audrey C. Smith; Mohammad Safaei; Mashoukur Rahaman; Ali Alruzuq; Bewuket B. Tefera; Carly S. Muir; Hannah V. Herrero

doi:10.3389/frsen.2024.1374862

journal article Open Access May 23, 2024

Machine learning versus deep learning in land system science: a decision-making framework for effective land classification

Jane Southworth

Audrey C. Smith

Mohammad Safaei Mashoukur Rahaman Ali Alruzuq Bewuket B. Tefera Carly S. Muir Hannah V. Herrero

Frontiers in Remote Sensing Vol. 5 · Frontiers Media SA

View at Publisher Save 10.3389/frsen.2024.1374862

Abstract

This review explores the comparative utility of machine learning (ML) and deep learning (DL) in land system science (LSS) classification tasks. Through a comprehensive assessment, the study reveals that while DL techniques have emerged with transformative potential, their application in LSS often faces challenges related to data availability, computational demands, model interpretability, and overfitting. In many instances, traditional ML models currently present more effective solutions, as illustrated in our decision-making framework. Integrative opportunities for enhancing classification accuracy include data integration from diverse sources, the development of advanced DL architectures, leveraging unsupervised learning, and infusing domain-specific knowledge. The research also emphasizes the need for regular model evaluation, the creation of diversified training datasets, and fostering interdisciplinary collaborations. Furthermore, while the promise of DL for future advancements in LSS is undeniable, present considerations often tip the balance in favor of ML models for many classification schemes. This review serves as a guide for researchers, emphasizing the importance of choosing the right computational tools in the evolving landscape of LSS, to achieve reliable and nuanced land-use change data.

Topics

No keywords indexed for this article. Browse by subject →

References

138

[1]

Abdi "Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data" GIScience Remote Sens. (2020) 10.1080/15481603.2019.1650447

[2]

Agrawal "Agricultural land suitability classification and crop suggestion using machine learning and spatial multicriteria decision analysis in semi-arid ecosystem" Environ. Dev. Sustain. (2024) 10.1007/s10668-023-04440-1

[3]

Ahmed "Dissolved oxygen concentration predictions for running waters with different land use land cover using a quantile regression forest machine learning technique" J. Hydrology (2021) 10.1016/j.jhydrol.2021.126213

[4]

Akar "Land use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information" Geocarto Int. (2022) 10.1080/10106049.2021.1945149

[5]

Alhassan "A deep learning framework for land-use/land-cover mapping and analysis using multispectral satellite imagery" Neural Comput. Appl. (2020) 10.1007/s00521-019-04349-9

[6]

Alshari "Classification of land use/land cover using artificial intelligence (ANN-RF)" Front. Artif. Intell. (2023) 10.3389/frai.2022.964279

[7]

Amini "Urban land use and land cover change analysis using random forest classification of Landsat time series" Remote Sens. (2022) 10.3390/rs14112654

[8]

ConvNetJS [JavaScript] AndrejA. 2022

[9]

Arruda "An alternative approach for mapping burn scars using Landsat imagery, Google Earth Engine, and Deep Learning in the Brazilian Savanna" Remote Sens. Appl. Soc. Environ. (2021) 10.1016/j.rsase.2021.100472

[10]

Aryal "Land use and land cover (LULC) performance modeling using machine learning algorithms: a case study of the city of Melbourne, Australia" Sci. Rep. (2023) 10.1038/s41598-023-40564-0

[11]

An overview of H2O: an open source AI platform open source for you BalakrishnanD. S. 2019

[12]

Barbierato "Integrating remote sensing and street view images to quantify urban forest ecosystem services" Remote Sens. (2020) 10.3390/rs12020329

[13]

Baylor "TFX: a TensorFlow-based production-scale machine learning platform" (2017)

[14]

Bhargava "A cloud computing-based approach to mapping mangrove erosion and progradation: case studies from the Sundarbans and French Guiana" Estuar. Coast. Shelf Sci. (2021) 10.1016/j.ecss.2020.106798

[15]

Bhosle "Evaluation of deep learning CNN model for land use land cover classification and crop identification using hyperspectral remote sensing images" J. Indian Soc. Remote Sens. (2019) 10.1007/s12524-019-01041-2

[16]

Campos-Taberner "Understanding deep learning in land use classification based on Sentinel-2 time series" Sci. Rep. (2020) 10.1038/s41598-020-74215-5

[17]

Campos-Taberner "Land use classification over smallholding areas in the European Common Agricultural Policy framework" ISPRS J. Photogrammetry Remote Sens. (2023) 10.1016/j.isprsjprs.2023.02.005

[18]

Chen "Multi-source remotely sensed data fusion for improving land cover classification" ISPRS J. Photogrammetry Remote Sens. (2017) 10.1016/j.isprsjprs.2016.12.008

[19]

Chen "Deep learning with edge computing: a review" Proc. IEEE (2019) 10.1109/jproc.2019.2921977

[20]

Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities

Gong Cheng, Junwei Han, Lei Guo et al.

IEEE Journal of Selected Topics in Applied Earth O... 2020 10.1109/jstars.2020.3005403

[21]

Application of Deep Learning in Multitemporal Remote Sensing Image Classification

Xinglu Cheng, Yonghua Sun, Wangkuan Zhang et al.

Remote Sensing 2023 10.3390/rs15153859

[22]

Cherif "DeepForest: novel deep learning models for land use and land cover classification using multi-temporal and -modal sentinel data of the Amazon basin" Remote Sens. (2022) 10.3390/rs14195000

[23]

Recent advances and applications of deep learning methods in materials science

Kamal Choudhary, Brian DeCost, Chi Chen et al.

npj Computational Materials 2022 10.1038/s41524-022-00734-6

[24]

(2022)

[25]

Davenport "How 'big data' is different" MITSloan Manag. Rev. (2012)

[26]

Delegido "Remote estimation of crop chlorophyll content by means of high‐spectral‐resolution reflectance techniques" Agron. J. 10.2134/agronj2011.0101

[27]

Delegido "Evaluation of sentinel-2 red-edge bands for empirical estimation of green LAI and chlorophyll content" Sensors 10.3390/s110707063

[28]

Delegido "A red-edge spectral index for remote sensing estimation of green LAI over agroecosystems" Eur. J. Agron. (2013) 10.1016/j.eja.2012.12.001

[29]

Du "Mapping forested wetland inundation in the Delmarva Peninsula, USA using deep convolutional neural networks" Remote Sens. (2020) 10.3390/rs12040644

[30]

Duffy "Perturbing parameters to understand cloud contributions to climate change" J. Clim. (2023) 10.1175/jcli-d-23-0250.1

[31]

Accounting for Training Data Error in Machine Learning Applied to Earth Observations

Arthur Elmes, Hamed Alemohammad, Ryan Avery et al.

Remote Sensing 2020 10.3390/rs12061034

[32]

Feizizadeh "Machine learning data-driven approaches for land use/cover mapping and trend analysis using Google Earth Engine" J. Environ. Plan. Manag. (2023) 10.1080/09640568.2021.2001317

[33]

Ferreira "Using remote sensing images and cloud services on AWS to improve land use and cover monitoring" (2020)

[34]

Fu "Easy over hard: a case study on deep learning" (2017)

[35]

Deep learning-based image recognition for autonomous driving

Hironobu Fujiyoshi, Tsubasa Hirakawa, Takayoshi Yamashita

IATSS Research 2019 10.1016/j.iatssr.2019.11.008

[36]

GDAL/OGR geospatial data abstraction software library open source geospatial foundation2024

[37]

Geist "Causes and trajectories of land-use/cover change" (2006) 10.1007/3-540-32202-7_3

[38]

Geng "High-resolution SAR image classification via deep convolutional autoencoders" IEEE Geoscience Remote Sens. Lett. (2015) 10.1109/lgrs.2015.2478256

[39]

Ghamisi "A self-improving convolution neural network for the classification of hyperspectral data" IEEE Geoscience Remote Sens. Lett. (2016) 10.1109/lgrs.2016.2595108

[40]

Github (2022)

[41]

Google Earth Engine: Planetary-scale geospatial analysis for everyone

Noel Gorelick, Matt Hancher, Mike Dixon et al.

Remote Sensing of Environment 2017 10.1016/j.rse.2017.06.031

[42]

Guidici "One-Dimensional convolutional neural network land-cover classification of multi-seasonal hyperspectral imagery in the San Francisco Bay Area, California" Remote Sens. (2017) 10.3390/rs9060629

[43]

Guo "Mapping large-scale mangroves along the maritime silk road from 1990 to 2015 using a novel deep learning model and Landsat data" Remote Sens. (2021) 10.3390/rs13020245

[44]

Gupta "Cloud detection in satellite images with classical and deep neural network approach: a review" Multimedia Tools Appl. (2022) 10.1007/s11042-022-12078-w

[45]

Gupta "Remote sensing image classification using deep learning" (2021)

[46]

Han "A survey of machine learning and deep learning in remote sensing of geological environment: challenges, advances, and opportunities" ISPRS J. Photogrammetry Remote Sens. (2023) 10.1016/j.isprsjprs.2023.05.032

[47]

Hermosilla "Land cover classification in an era of big and open data: optimizing localized implementation and training data selection to improve mapping outcomes" Remote Sens. Environ. (2022) 10.1016/j.rse.2021.112780

[48]

Hibbard "Research priorities in land use and land‐cover change for the Earth system and integrated assessment modelling" Int. J. Climatol. (2010) 10.1002/joc.2150

[49]

Holloway "Statistical machine learning methods and remote sensing for sustainable development goals: a review" Remote Sens. (2018) 10.3390/rs10091365

[50]

Hong "Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning model" ISPRS J. Photogrammetry Remote Sens. (2021) 10.1016/j.isprsjprs.2021.05.011

Showing 50 of 138 references

Metrics

27

Citations

138

References

Details

Published: May 23, 2024
Vol/Issue: 5
License: View

Authors

University of Florida

Cite This Article

Jane Southworth, Audrey C. Smith, Mohammad Safaei, et al. (2024). Machine learning versus deep learning in land system science: a decision-making framework for effective land classification. Frontiers in Remote Sensing, 5. https://doi.org/10.3389/frsen.2024.1374862

Machine learning versus deep learning in land system science: a decision-making framework for effective land classification

You May Also Like