A Revolutionary Workflow for Petroleum Reservoir Evaluation: Integrating VNIR-LWIR Spectroscopy and Machine Learning

在地質勘探領域(yù)，如何(hé)快速，準(zhǔn)確(què)地(dì)從數百米(mǐ)長的岩心(xīn)中找到最(zuì)關(guān)鍵(jiàn)的那(nà)幾塊(kuài)樣本，一直(zhí)是個(gè)巨大挑戰。一項針(zhēn)對(duì)沙(shā)特阿拉伯油(yóu)氣儲層的研究，展(zhǎn)示(shì)了(liǎo)一(yī)種具(jù)有(yǒu)前景(jǐng)的(dí)解(jiě)決(jué)方(fāng)案。

In the field of geological exploration, rapidly and accurately identifying the most critical samples from hundreds of meters of core has long been a significant challenge. A study focusing on hydrocarbon reservoirs in Saudi Arabia demonstrates a highly promising solution.

注：

地質(zhì)勘探是(shì)指(zhǐ)為(wéi)了(liǎo)查(chá)明(míng)地下(xià)地質情況(kuàng)，探尋礦產資源(yuán)（如(rú)油氣(qì)，礦(kuàng)產(chǎn)，地下水等(děng)）而(ér)開(kāi)展的一(yī)係列(liè)綜合性調查與(yǔ)研究工作。對於油氣(qì)領(lǐng)域而言，地質勘(kān)探(tàn)的(dí)核心任務是確定油氣聚(jù)集的有(yǒu)利區域，並(bìng)最終(zhōng)定位可(kě)供(gōng)開采的油氣藏(cáng)。

油氣儲(chǔ)層是地下(xià)具備(bèi)儲(chǔ)集空(kōng)間（孔隙(xì)，裂縫）和流(liú)體滲流(liú)能(néng)力(lì)（滲(shèn)透性）的岩(yán)層，油(yóu)氣就儲(chǔ)存(cún)於(yú)這(zhè)些(xiē)空(kōng)間內。它(tā)是(shì)油氣藏(cáng)形(xíng)成(chéng)的(dí)核(hé)心要素之(zhī)一。最(zuì)常見的油(yóu)氣(qì)儲層岩石(shí)類型(xíng)是砂岩(yán)和碳酸鹽岩(yán)（如石灰岩，白(bái)雲(yún)岩）。

通過地(dì)質(zhì)勘(kān)探(tàn)，來發(fā)現(xiàn)，圈定(dìng)和評價具有(yǒu)商業價值的(dí)油氣儲(chǔ)層(céng)。

Note:

Geological Exploration refers to a series of comprehensive investigations and research activities conducted to understand subsurface geological conditions and explore for mineral resources (such as oil, gas, minerals, groundwater, etc.). In the context of the petroleum industry, the core objective of geological exploration is to identify areas favorable for hydrocarbon accumulation and ultimately locate exploitable oil and gas reservoirs.

A Hydrocarbon Reservoir is a subsurface rock unit possessing storage space (pores, fractures) and the ability to allow fluid flow (permeability); hydrocarbons are stored within these spaces. It is one of the core elements for the formation of a hydrocarbon accumulation. The most common rock types for hydrocarbon reservoirs are sandstones and carbonates (e.g., limestone, dolomite).

The purpose of geological exploration is to discover, delineate, and evaluate commercially viable hydrocarbon reservoirs.

研(yán)究(jiū)地(dì)區(qū)（Wadi Daqlah）出露岩相的(dí)綜(zōng)合岩石(shí)地層柱狀圖(tú) / the generalized lithostratigraphy of exposed facies in  the study area (Wadi Daqlah)

「光譜範(fàn)圍」

在(zài)這(zhè)項(xiàng)研(yán)究(jiū)的(dí)核(hé)心技(jì)術基礎(chǔ)是全(quán)波段高光譜成(chéng)像(xiàng)，光譜範圍覆蓋了(liǎo)從(cóng)可見光到(dào)長波(bō)紅外(wài)的(dí)廣(guǎng)闊區(qū)間(jiān)：

可(kě)見光(guāng)-近紅外(wài) (VNIR, 400-1000 nm)：主(zhǔ)要對岩(yán)石(shí)中(zhōng)的鐵(tiě)離子（Fe²⁺）等過(guò)渡金屬元素(sù)敏(mǐn)感(gǎn)。通過計算鐵指(zhǐ)數，可以(yǐ)快(kuài)速評(píng)估岩石(shí)的(dí)化(huà)學組成(chéng)變化。

短波紅外 (SWIR, 1000-2500 nm)：方解(jiě)石和白雲石(shí)在(zài)此區域(yù)的特(tè)征吸收穀位置(zhì)，存在(zài)約20納(nà)米(mǐ)的微(wēi)小但穩定(dìng)的(dí)偏(piān)移（方(fāng)解石~2345 nm，白(bái)雲(yún)石(shí)~2325 nm）。這個差異(yì)是快速，準確繪(huì)製礦物分(fēn)布(bù)圖(tú)的關鍵。

中波紅外 (MWIR, 3-7μm) 與(yǔ)長(cháng)波(bō)紅外(wài) (LWIR, 8-14μm)：包含(hán)了碳(tàn)酸(suān)鹽(yán)礦(kuàng)物更復(fù)雜的分(fēn)子(zǐ)振動信(xìn)息(xī)。本(běn)研(yán)究通(tōng)過融(róng)合(hé)這(zhè)三個(gè)紅(hóng)外區(qū)間的數(shù)據(jù)，能(néng)夠捕捉到(dào)單(dān)靠SWIR無法識別的，與(yǔ)岩(yán)石(shí)晶(jīng)體結構和粒(lì)度相(xiāng)關(guān)的細微差異(yì)，從而成功(gōng)區(qū)分了不同(tóng)結(jié)構的白雲(yún)岩。

「Spectral Range」

The core technical foundation of this study is full-range hyperspectral imaging, covering a broad spectrum from the visible to the long-wave infrared:

Visible-Near Infrared (VNIR, 400-1000 nm): This range is primarily sensitive to transition metal elements such as ferrous iron (Fe²⁺) in rocks. Calculating an iron index allows for rapid assessment of changes in the rock's chemical composition.

Short-Wave Infrared (SWIR, 1000-2500 nm): A key finding of the study is the consistent, approximately 20-nanometer shift in the characteristic absorption trough positions between calcite and dolomite in this region (calcite ~2345 nm, dolomite ~2325 nm). This difference is crucial for rapidly and accurately mapping mineral distribution.

Mid-Wave Infrared (MWIR, 3-7μm) and Long-Wave Infrared (LWIR, 8-14μm): These ranges contain more complex molecular vibration information from carbonate minerals. By integrating data from these three infrared intervals, the study was able to detect subtle differences related to rock crystal structure and grain size that are indistinguishable using SWIR alone, thereby successfully differentiating dolomites with varying textures.

白(bái)雲岩（綠）與方(fāng)解(jiě)石（藍）的(dí)光譜(pǔ)特(tè)征(zhēng)：白(bái)雲岩的特征吸收(shōu)峰位置(zhì)約為2325nm，方(fāng)解石的(dí)特(tè)征吸(xī)收峰位置約為2345nm。

Spectral signature of dolomite (green) and calcite (blue) with characteristic absorption band position around 2325 nm (dashed green line) for dolomite and 2345 nm (dashed blue line) for calcites.

「基(jī)於高光譜成(chéng)像的數據分(fēn)析工作流程(chéng)」

傳(chuán)統地(dì)質(zhì)采樣(yàng)可(kě)被視(shì)為(wéi)“經(jīng)驗(yàn)驅(qū)動"模(mó)式(shì)，嚴重(zhòng)依賴專家(jiā)的肉(ròu)眼觀(guān)察和主觀判(pàn)斷。本研(yán)究(jiū)提(tí)出一套更客(kè)觀的，更(gēng)高(gāo)效，可重復(fù)的(dí)“數據驅動"解(jiě)決(jué)方案(àn)，其(qí)工作流(liú)程(chéng)清(qīng)晰(xī)體現了從宏(hóng)觀到(dào)微觀的分(fēn)析邏輯：

第(dì)一步(bù)：全(quán)域掃描，繪製礦物地(dì)圖。研(yán)究團隊首(shǒu)先(xiān)利用SWIR波(bō)段(duàn)特(tè)征(zhēng)，對50米長(cháng)的岩心進(jìn)行快速掃(sǎo)描，生(shēng)成(chéng)一張(zhāng)高精度的礦物分布(bù)圖，清(qīng)晰界定出(chū)白(bái)雲石化的目(mù)標(biāo)區(qū)域。

第二步(bù)：識別結構(gòu)差異(yì)。在(zài)鎖定白(bái)雲石區域後(hòu)，通過綜合(hé)SWIR，MWIR和LWIR的光譜(pǔ)信(xìn)息(xī)，並采(cǎi)用主(zhǔ)成(chéng)分分析（PCA）算(suàn)法(fǎ)，係統能夠(gòu)放(fàng)大那些(xiē)與晶體(tǐ)結(jié)構(gòu)，粒度相(xiāng)關(guān)的細微光譜差(chà)異(yì)。這些差異(yì)是肉眼無法分辨(biàn)的。

第三步(bù)：定位(wèi)最(zuì)佳(jiā)采(cǎi)樣(yàng)點(diǎn)。基(jī)於光譜(pǔ)差異(yì)，K-means聚(jù)類(lèi)算法將(jiāng)白雲石像素自動劃(huá)分(fēn)為(wéi)4個類(lèi)別(bié)。隨(suí)後，係(xì)統會計算(suàn)出每(měi)個(gè)類別(bié)的光譜中心，並推(tuī)薦最(zuì)靠(kào)近這些(xiē)中(zhōng)心的岩心位置作(zuò)為具(jù)代表性的采(cǎi)樣(yàng)點。

「Data-Driven Workflow Based on Hyperspectral Imaging」

Traditional geological sampling can be considered an "experience-driven" model, heavily reliant on experts' visual observation and subjective judgment. This study proposes a more objective, efficient, and reproducible "data-driven" solution. The workflow clearly demonstrates an analytical logic progressing from macro to micro:

1. Full-Scene Scanning and Mineral Mapping: The research team first utilized SWIR spectral features to rapidly scan the 50-meter core, generating a high-precision mineral distribution map that clearly delineated the target dolomitized zones.

2. Identifying Textural Differences: After identifying the dolomite regions, the system amplified subtle spectral differences related to crystal structure and grain size by integrating spectral information from SWIR, MWIR, and LWIR and applying Principal Component Analysis (PCA). These differences are entirely undetectable to the naked eye.

3. Locating Optimal Sampling Points: Based on the spectral differences, the K-means clustering algorithm automatically classified the dolomite pixels into four categories. The system then calculated the spectral centroid for each category and recommended the core locations closest to these centroids as the most representative sampling points.

A. 標準化混淆(xiáo)矩陣，展(zhǎn)示(shì)基於(yú)岩相學(xué)分析與(yǔ)高光(guāng)譜成像(xiàng)分(fēn)析的(dí)白雲岩結(jié)構(gòu)分類結(jié)果（對(duì)比(bǐ)）。B. 針對(duì)相同(tóng)的(dí)岩芯取(qǔ)樣(yàng)點樣品（該樣(yàng)品同時用(yòng)於(yú)ICP-OES實驗(yàn)室(shì)檢測），高光(guāng)譜(pǔ)成像(xiàng)計(jì)算得出的鐵指(zhǐ)數(shù)與(yǔ)鐵(tiě)濃度之間的(dí)相關(guān)性分析(xī)圖。

A. Normalized confusion matrix showing the dolomite texture classification from petrographic analysis and HSI based classification. B. Correlation between HSI derived iron index and Fe concentration for the same plug samples used for ICP-OES lab measurements.

A.不(bù)同類(lèi)型白(bái)雲(yún)岩沿岩芯(xīn)的分(fēn)類(lèi)及(jí)分布情(qíng)況(kuàng)。各類(lèi)別(bié)白雲岩在(zài)B.可見(jiàn)近紅(hóng)外-短(duǎn)波紅外（VNIR-SWIR）波(bō)段，C.中波紅(hóng)外（MWIR）波段，D.長波紅外（LWIR）波(bō)段(duàn)的(dí)代(dài)表(biǎo)性(xìng)光(guāng)譜。

A. Classification and distribution of the different dolomite types along the drill core. Representative spectra for each class in the VNIR- SWIR (B.), MWIR (B) and LWIR(C).

「結語(yǔ)」

綜上所述(shù)，這(zhè)篇論(lùn)文(wén)的(dí)亮點在(zài)於(yú)：它展(zhǎn)示了一(yī)個從全(quán)域掃(sǎo)描到采樣(yàng)的(dí)完整數據驅動(dòng)工作流程(chéng)，為地(dì)質(zhì)研究提供了(liǎo)新思(sī)路(lù)；同(tóng)時(shí)，它(tā)突破了(liǎo)常(cháng)規，通過集(jí)成VNIR-SWIR-MWIR-LWIR多波段(duàn)數據(jù)，實(shí)現了(liǎo)對(duì)碳(tàn)酸鹽岩(yán)從(cóng)礦物識別到(dào)結構(gòu)分類(lèi)的精(jīng)細刻(kè)畫。

這(zhè)不僅對油氣行(háng)業有直接價值，也為(wéi)未來(lái)在(zài)礦產(chǎn)勘查等領域(yù)的精細(xì)表(biǎo)征指明了方向(xiàng)。

如(rú)果您想了解(jiě)可見(jiàn)光(guāng)-近紅(hóng)外，短波紅外波段，甚(shèn)至是(shì)中波紅外或長波(bō)紅外波(bō)段(duàn)的高(gāo)光譜(pǔ)成像(xiàng)係(xì)統，歡迎聯(lián)係(xì)我(wǒ)們(mén)！

「Conclusion」

In summary, the highlights of this paper are twofold: it demonstrates a complete data-driven workflow from full-scene scanning to sampling, providing a new paradigm for geological research; furthermore, it breaks from convention by integrating VNIR-SWIR-MWIR-LWIR multi-band data to achieve fine characterization of carbonate rocks, progressing from mineral identification to texture classification.

This holds direct value for the petroleum industry and also points the way for detailed characterization in future applications such as mineral exploration.

If you are interested in hyperspectral imaging systems covering the VNIR, SWIR, or even MWIR and LWIR ranges, please do not hesitate to contact us!

論(lùn)文 / Article：

Gairola, G. S., Thiele, S. T., Khanna, P., Ramdani, A. I., Gloaguen, R., & Vahrenkamp, V. (2024). A data-driven hyperspectral method for sampling of diagenetic carbonate fabrics – A case study using an outcrop analogue of Jurassic Arab-D reservoirs, Saudi Arabia. Marine and Petroleum Geology, 161, 106691.