Restricted accessResearch articleFirst published online 2025-12
Integrating Machine Learning,Remote Sensing,and a Geographic Information System to Determine Road Surface Type and Construction Year from High-Resolution and Multispectral Aerial Imagery: A Case Study in Ames,Iowa
Road pavement data plays a crucial role in establishing an effective pavement management system and enables agencies to make more accurate decisions on maintenance and rehabilitation plans. Traditional pavement data collection methods are time-consuming, costly, and labor-intensive, limiting their scalability for large-scale infrastructure assessment. Utilizing satellite/aerial imagery for extracting road pavement data is becoming increasingly popular because of the availability of high-resolution images, advancements in image processing and remote sensing techniques, enhanced computational power, and the presence of geographic information systems (GISs). This novel study integrates machine learning (ML), remote sensing, and a GIS to develop an automated tool based on a robust deep-learning model to extract the construction year from time-series aerial imagery. This study also employs pixel classification to automate differentiation between asphalt concrete (AC) and Portland cement concrete (PCC) road surface pixels using multispectral aerial imagery. The study area is the city of Ames in Story County, Iowa, where the model’s performance is rigorously assessed. Results demonstrate high accuracy in predicting road construction years, achieving 94% for both recall and precision. The AC and PCC surfaces were classified with 89% overall accuracy, 95.38% and 77.14% recall rates, respectively, and PCC demonstrated a high precision of 90%, compared to AC’s 88.57%. This study underscores the need for high-resolution multispectral imagery (30 cm or less) captured in spring with cloud cover below 10% for optimal accuracy. These findings highlight the potential of remote sensing and ML in improving pavement data collection, enhancing accuracy, and reducing manual effort. Higher-resolution imagery with an extended spectrum can further improve accuracy.
JalayerM.HuS.ZhouH.TurochyR. E.Evaluation of Geo-Tagged Photo and Video Logging Methods to Collect Geospatial Highway Inventory Data. Papers in Applied Geography, Vol. 1, No. 1, 2015, pp. 50–58.
2.
ChandranS.IsaacK.VeeraragavanA.Prioritization of Low-Volume Pavement Sections for Maintenance by Using Fuzzy Logic. Transportation Research Record: Journal of the Transportation Research Board, 2007. 1989: 53–60.
3.
ElbagalatiO.ElseifiM.GaspardK.ZhangZ.Implementation of the Structural Condition Index into the Louisiana Pavement Management System Based on Rolling Wheel Deflectometer Testing. Transportation Research Record: Journal of the Transportation Research Board, 2017. 2641: 39–47.
4.
RadočajD.JurišićM.GašparovićM.The Role of Remote Sensing Data and Methods in a Modern Approach to Fertilization in Precision Agriculture. Remote Sensing, Vol. 14, No. 3, 2022, p. 778. https://doi.org/10.3390/rs14030778.
5.
PanY.ShangY.LiuG.XieY.ZhangC.ZhaoY.Cost-Effectiveness Evaluation of Pavement Maintenance Treatments Using Multiple Regression and Life-Cycle Cost Analysis. Construction and Building Materials, Vol. 292, 2021, p. 123461.
6.
SongY.WrightG.WuP.ThatcherD.McHughT.LiQ.LiS. J.WangX.Segment-Based Spatial Analysis for Assessing Road Infrastructure Performance Using Monitoring Observations and Remote Sensing Data. Remote Sensing, Vol. 10, No. 11, 2018, p. 1696. https://doi.org/10.3390/rs10111696.
7.
ChengL.ZhangX.ShenJ.Road Surface Condition Classification Using Deep Learning. Journal of Visual Communication and Image Representation, Vol. 64, 2019, p. 102638.
8.
ŠabanovičE.ŽuraulisV.PrentkovskisO.SkrickijV.Identification of Road-Surface Type Using Deep Neural Networks for Friction Coefficient Estimation. Sensors, Vol. 20, No. 3, 2020, p. 612.
9.
LiN.HaasR.XieW.Investigation of Relationship Between Deterministic and Probabilistic Prediction Models in Pavement Management. Transportation Research Record: Journal of the Transportation Research Board, 1997. 1592: 70–79.
10.
OliveiraJ.DavisG.KhaniA.MarasteanuM.Heterogeneous Markov Chain Model to Predict Pavement Performance and Deterioration. Transportation Research Record: Journal of the Transportation Research Board, 2022. 2676: 568–581.
LakoK.GjevoriR.Road Maintenance Planning of the Fier-Vlore Road Axis, Based on the Assessment and Forecast of AADT and LOS Service Level. Qubahan Academic Journal, Vol. 4, No. 1, 2024, pp. 62–71. https://doi.org/10.58429/qaj.v4n1a269.
13.
TangJ.LiD.ZhangW.Research on Intelligent Detection of Pavement Damage Based on CNN. Mathematical Models in Engineering, Vol. 8, No. 2, 2022, pp. 217–228. https://doi.org/10.21595/mme.2022.22918.
14.
DiegoA.AbdulhabibK.PimientoJ.Vision-Based Road Detection via on-Line Video Registration. Proc., IEEE Intelligent Transportation Systems Conference, Funchal, Portugal, IEEE, New York, September 19–22, 2010, pp. 123–128. https://doi.org/10.1109/itsc.2010.5624998.
15.
LubisN.LubisA.SupriyadiD.Implementation of KNN Methods and GLCM Extraction for Classification of Road Damage Level. IAIC Transactions on Sustainable Digital Innovation (ITSDI), Vol. 4, No. 1, 2022, pp. 110–117. https://doi.org/10.34306/itsdi.v4i1.564.
BaoH.JiangY.ZhaoY.Unpaved Road Detection Based on Spatial Fuzzy Clustering Algorithm. Eurasip Journal on Image and Video Processing, Vol. 2018, No. 1, 2018, p. 260. https://doi.org/10.1186/s13640-018-0260-3.
ZhangS.LippittC.BogusS.NevilleP.Characterizing Pavement Surface Distress Conditions with Hyper-Spatial Resolution Natural Color Aerial Photography. Remote Sensing, Vol. 8, No. 5, 2016, p. 392. https://doi.org/10.3390/rs8050392.
20.
WorkmanR.WongP.WrightA.WangZ.Prediction of Unpaved Road Conditions Using High-Resolution Optical Satellite Imagery and Machine Learning. Remote Sensing, Vol. 15, No. 16, 2023, p. 3985.
21.
CadamuroG.MuhebwaA.TanejaJ.Street Smarts: Measuring Intercity Road Quality Using Deep Learning on Satellite Imagery. Proc., 2nd ACM SIGCAS Conference on Computing and Sustainable Societies, Accra, Ghana, Association for Computing Machinery, New York, NY, July 3–5, 2019, pp. 145–154. https://doi.org/10.1145/3314344.3332493.
22.
AntwiR. B.TakyiS.KaraerA.OzguvenE. E.MosesR.DulebenetsM. A.SandoT.Detecting School Zones on Florida’s Public Roadways Using Aerial Images and Artificial Intelligence (AI2). Transportation Research Record: Journal of the Transportation Research Board, 2024. 2678: 622–636.
23.
AntwiR. B.TakyiS.MichaelK.KaraerA.OzguvenE. E.MosesR.DulebenetsM. A.SandoT.Computer Vision-Based Model for Detecting Turning Lane Features on Florida’s Public Roadways. arXiv preprint arXiv:2406.08822, June13, 2024.
24.
TanY.LiY.Uav Photogrammetry-Based 3d Road Distress Detection. ISPRS International Journal of Geo-Information, Vol. 8, No. 9, 2019, p. 409. https://doi.org/10.3390/ijgi8090409.
25.
RobertsR.InzerilloL.MinoG.Using UAV Based 3D Modelling to Provide Smart Monitoring of Road Pavement Conditions. Information, Vol. 11, No. 12, 2020, p. 568. https://doi.org/10.3390/info11120568.
26.
RahnamayiezekavatP.WangD.ChaiJ.MoonS.RashidiM.WangX.Automated Pavement Marking Integrity Assessment Using a UAV Platform–a Test Case of Public Parking. Journal of Asian Architecture and Building Engineering, Vol. 24, No. 3, 2025, pp. 1594–1605.
27.
SimoesR.CamaraG.QueirozG.SouzaF.AndradeP. R.SantosL.CarvalhoA.FerreiraK.Satellite Image Time Series Analysis for Big Earth Observation Data. Remote Sensing, Vol. 13, No. 13, 2021, p. 2428.
28.
OehmckeS.ThrysøeC.BorgstadA.SallesM. A.BrandtM.GiesekeF.Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. Proc., IEEE International Conference on Big Data (Big Data), Los Angeles, CA, IEEE, New York, December9, 2019, pp. 2403–2412.
29.
AntwiR. B.TakyiS.KaraerA.OzguvenE. E.KimolloM.MosesR.DulebenetsM. A.SandoT.Automated GIS-Based Framework for Detecting Crosswalk Changes from Bi-Temporal High-Resolution Aerial Images. arXiv preprint arXiv:2406.09731, June14, 2024.
30.
LiangS.SchaepmanM.KneubühlerM.Remote Sensing Signatures: Measurements, Modelling and Applications. In Advances in Photogrammetry, Remote Sensing and Spatial Information Sciences: 2008 ISPRS Congress Book (Z.LiChenJ.BaltsaviasE., eds.), CRC Press, London, 2008, pp. 145–162. https://doi.org/10.1201/9780203888445-17.
31.
AndréfouëtS.PayriC.HochbergE.HuC.AtkinsonM.Muller-KargerF.Use of in Situ and Airborne Reflectance for Scaling-up Spectral Discrimination of Coral Reef Macroalgae from Species to Communities. Marine Ecology Progress Series, Vol. 283, 2004, pp. 161–177. https://doi.org/10.3354/meps283161.
32.
LanglentombiL.Development of Spectral Signature of Chir Pine Using Hyperion Data. International Journal of Bio-Resource and Stress Management, Vol. 15, 2024, pp. 1–6. https://doi.org/10.23910/1.2024.5026.
HeroldM.RobertsD.NoronhaV.SmadiO.Imaging Spectrometry and Asphalt Road Surveys. Transportation Research Part C: Emerging Technologies, Vol. 16, No. 2, 2008, pp. 153–166.
35.
ChenX.ZhangX.LiJ.RenM.ZhouB.A New Method for Automated Monitoring of Road Pavement Aging Conditions Based on Recurrent Neural Network. IEEE Transactions on Intelligent Transportation Systems, Vol. 23, No. 12, 2022, pp. 24510–24523.
36.
WangH.YangD.XieZ.WangJ.HaoZ.ZhouF.WangX.Assessment of Asphalt Pavement Aging Condition Based on GF-2 High-Resolution Remote Sensing Image. Journal of Applied Remote Sensing, Vol. 18, No. 1, 2024, p. 014528.
37.
BrewerE.LinJ.KemperP.HenninJ.RunfolaD.Predicting Road Quality Using High Resolution Satellite Imagery: A Transfer Learning Approach. PLoS One, Vol. 16, No. 7, 2021, p. e0253370.
38.
BastaniF.MaddenS.Beyond Road Extraction: A Dataset for Map Update Using Aerial Images. Proc., IEEE/CVF International Conference on Computer Vision, 2021, pp. 11905–11914. https://doi.org/10.1109/iccv48922.2021.01169.
39.
AbdollahiA.PradhanB.ShuklaN.ChakrabortyS.AlamriA.Deep Learning Approaches Applied to Remote Sensing Datasets for Road Extraction: A State-of-the-Art Review. Remote Sensing, Vol. 12, No. 9, 2020, p. 1444.
40.
MerkleN.HenryC.AzimiS. M.KurzF.Road Condition Assessment from Aerial Imagery Using Deep Learning. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 2, 2022, pp. 283–289.
41.
HamunzalaB.MatsumotoK.NagaiK.Improved Method for Estimating Construction Year of Road Bridges by Analyzing Landsat Normalized Difference Water Index 2. Remote Sensing, Vol. 15, No. 14, 2023, p. 3488.
42.
ValleD.RifaiS. W.CarreroG. C.MeigaA. Y.An Automated Procedure to Determine Construction Year of Roads in Forested Landscapes Using a Least-Cost Path and a Before-After Control-Impact Approach. Remote Sensing in Ecology and Conservation, Vol. 10, No. 3, 2024, pp. 388–400.
43.
RatekeT.JustenK. A.Von WangenheimA.Road Surface Classification with Images Captured from Low-Cost Camera-Road Traversing Knowledge (RTK) Dataset. Revista de Informática Teórica e Aplicada, Vol. 26, No. 3, 2019, pp. 50–64.
44.
Berber-SolanoT. P.AjovalasitM.GiacominJ.Facilitating the Driver Detection of Road Surface Type by Selective Manipulation of the Steering-Wheel Acceleration Signal. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, Vol. 224, No. 10, 2010, pp. 1321–1333.
Analytics Bureau > Roadway Asset Management System > Annual Miles of Public Road by Surface Type. iowadot.gov.
49.
Road Network (Portal). Iowa Department of Transportation - Open Data. iowadot.gov.
50.
City. Iowa Department of Transportation - Open Data. iowadot.gov.
51.
CaruanaR.Multitask Learning. Machine Learning, Vol. 28, 1997, pp. 41–75.
52.
BatraA.SinghS.PangG.BasuS.JawaharC. V.PaluriM.Improved Road Connectivity by Joint Learning of Orientation and Segmentation. Proc., IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10385–10393. https://doi.org/10.1109/cvpr.2019.01063.
53.
GilbertR. C.TrafalisT. B.Support Vector Machines Applied to Multivariate Processes. In Intelligent Engineering Systems through Artificial Neural Networks (C. H.Dagli, ed.), Vol. 20, ASME Press, New York, NY, 2010.
54.
CampbellC.YingY.Learning with Support Vector Machines, No. 10. Morgan & Claypool Publishers, 2011.
55.
WiedemannC.HeipkeC.MayerH.JametO.Empirical Evaluation of Automatically Extracted Road Axes. Empirical Evaluation Techniques in Computer Vision, Vol. 12, 1998, pp. 172–187.
