高頻（High Frequency， HF）電波可經由電離層折射形成超視距天波傳播，其傳播路徑與可用頻率會受到電離層電子密度、Es layer、地磁場及水平電子密度變化等因素影響。本研究主要利用垂直與斜向電離層探測、高頻通訊實驗、固定與移動式遠距接收，以及三維射線追蹤方法，分析臺灣及周邊海域之高頻天波傳播特性，並探討由電離層觀測結果推估實際斜向傳播條件與通訊可行性。 本研究首先利用中壢垂直 ionogram 與滿州斜向 ionogram，建立中壢—滿州約 309 km 固定斜向天波鏈路之 transmission curve 分析方法，推算反射虛高、反射點電漿頻率、入射角與地表傳播距離。結果顯示，不同時段與頻率下之平均距離誤差絕對值約為 0.01–2.48 km，相對誤差最高約 0.8%。將相同方法延伸至 659 km 傳播距離後，平均距離誤差絕對值約為 0.40–4.83 km，相對誤差約為 0.061%–0.733%，顯示 transmission curve 配合實測 ionogram 可有效推估固定斜向鏈路之地表傳播距離。此外，本研究分析中壢—滿州鏈路之日出瞬變現象，日出期間 F layer 反射虛高下降率約可達 83 km/hr，入射角增加率約可達 9°/hr。Es layer 傳播結果之平均地表距離為 311.5 km，標準差為 3.5 km，與實際 309 km 鏈路距離之平均相對誤差約為 0.78%。 在實際高頻通訊部分，本研究建立中壢—東沙島約 659 km 天波通訊實驗鏈路，將 Barker code 加碼之 BPSK 數位訊號轉換為通訊機可處理之語音頻帶音訊訊號，再利用 H2010 高頻通訊機進行天波發射與接收。接收資料經同步、頻率偏移估測、相位補償及相關解碼後，未進行相位補償時之整體解碼成功率約為 5.6%–21.2%，加入相位補償後提升至約 64.7%–86.2%；進一步使用 PCA 與 PLL 進行相位校正後，最高成功率分別可達 88.9% 與 89.6%，顯示接收訊號之相位變化為影響實際天波數位通訊解碼的重要因素。本研究亦發現，增加 Barker code 重複次數雖可提高理論處理增益，但過長之訊文時間會受到電離層通道相位變化影響，使解碼效能反而下降。 此外，本研究整合 H2010 sounding mode、MUF 預報、中壢 ionogram 及勵進號船載接收資料，分析固定與移動接收條件下之 HF 傳播特性，並建立由 sounding mode 斜向觀測結果轉換為等效垂直電離層參數之方法，使通訊機觀測資料可進一步與 ionogram 進行比較，作為分析岸基發射至遠距固定或移動接收端傳播條件之依據。 最後，本研究建立三維 ray tracing 模擬流程，結合 IRI 電子密度模型與 IGRF 地磁場模型，並以 PHaRLAP 進行交叉驗證。於無水平電子密度梯度條件下，本研究與 PHaRLAP 所得到之射線落點與地表距離具有相近分布，顯示所建立之 ray tracing 流程可重現不同地磁及 O-wave、X-wave 條件下之傳播特性。進一步比較固定點對點地表距離估算結果，中壢—滿州 309 km 鏈路在無地磁場、O-wave 與 X-wave 三種 ray tracing 設定下之平均絕對距離偏差約為 8.73 km，而 transmission curve 結合實測 ionogram 後約為 0.70 km；659 km 傳播距離之兩者誤差則分別約為 37.17 km 與 1.58 km，ray tracing 之平均絕對距離偏差分別約為 transmission curve 方法的 12.4 倍與 23.5 倍。結果顯示，ray tracing 適合分析地磁場、射線型態與三維電子密度結構對傳播路徑之影響，而結合實際 ionogram 之 transmission curve 對固定點對點地表距離具有較穩定之估算結果。;High-frequency (HF) radio waves can propagate beyond the line of sight through refraction in the ionosphere. Their propagation paths and usable frequencies are affected by factors such as ionospheric electron density， sporadic E (Es) layers， the geomagnetic field， and horizontal variations in electron density. This study investigates HF skywave propagation over Taiwan and the surrounding seas using vertical and oblique ionospheric sounding， HF communication experiments， fixed and mobile remote reception， and three-dimensional ray tracing. The applicability of ionospheric observations to the estimation of practical oblique propagation conditions and HF communication feasibility is also examined. First， vertical ionograms observed at Zhongli and oblique ionograms received at Manzhou were used to establish a transmission-curve analysis method for the approximately 309-km fixed oblique skywave link between Zhongli and Manzhou. The virtual reflection height， plasma frequency at the reflection point， incidence angle， and ground propagation distance were estimated. The results show that the absolute values of the mean distance errors under different time periods and frequencies ranged from approximately 0.01 to 2.48 km， with a maximum relative error of approximately 0.8%. When the same method was extended to a propagation distance of 659 km， the absolute values of the mean distance errors ranged from approximately 0.40 to 4.83 km， corresponding to relative errors of approximately 0.061%–0.733%. These results demonstrate that the transmission-curve method combined with measured ionograms can effectively estimate the ground propagation distance of fixed oblique links. In addition， sunrise transient variations along the Zhongli–Manzhou link were analyzed. During sunrise， the F-layer virtual reflection height decreased at a rate of up to approximately 83 km/hr， while the incidence angle increased at a rate of up to approximately 9°/hr. For Es-layer-supported propagation， the mean estimated ground distance was 311.5 km with a standard deviation of 3.5 km， corresponding to a mean relative error of approximately 0.78% compared with the actual 309-km link distance. For the practical HF communication experiment， an approximately 659-km skywave communication link was established between Zhongli and Dongsha Island. Barker-code-encoded BPSK digital signals were converted into voice-band audio signals that could be processed by the HF transceiver and were then transmitted and received through H2010 HF transceivers. The received data were processed using synchronization， frequency-offset estimation， phase compensation， and correlation-based decoding. Without phase compensation， the overall decoding success rate was approximately 5.6%–21.2%. After phase compensation， the success rate increased to approximately 64.7%–86.2%. With further phase correction using principal component analysis (PCA) and a phase-locked loop (PLL)， the maximum success rates reached 88.9% and 89.6%， respectively. These results indicate that phase variations in the received signal are a major factor affecting the decoding performance of practical HF skywave digital communication. The results also show that， although increasing the number of Barker-code repetitions can theoretically provide greater processing gain， an excessively long message duration is more strongly affected by ionospheric channel phase variations and may consequently reduce decoding performance. In addition， H2010 sounding-mode observations， maximum usable frequency (MUF) predictions， Zhongli ionograms， and shipborne receiving data obtained onboard the R/V LEGEND were integrated to investigate HF propagation characteristics under fixed and mobile receiving conditions. A method was also established to convert oblique sounding-mode observations into equivalent vertical ionospheric parameters， allowing measurements obtained from the HF communication system to be further compared with ionograms. This provides a basis for analyzing propagation conditions from a shore-based transmitter to distant fixed or mobile receivers. Finally， a three-dimensional ray-tracing procedure was developed by combining the International Reference Ionosphere (IRI) electron-density model with the International Geomagnetic Reference Field (IGRF)， and the results were cross-validated against PHaRLAP. Under conditions without horizontal electron-density gradients， the ray landing points and ground-distance distributions obtained from the developed method were similar to those obtained from PHaRLAP， demonstrating that the developed ray-tracing procedure can reproduce propagation characteristics under different geomagnetic-field assumptions and O-wave and X-wave conditions. For fixed point-to-point ground-distance estimation， the mean absolute distance deviation of the Zhongli–Manzhou 309-km link under the three ray-tracing settings of no magnetic field， O-wave， and X-wave was approximately 8.73 km， whereas the transmission-curve method combined with measured ionograms yielded approximately 0.70 km. For the 659-km propagation distance， the corresponding deviations were approximately 37.17 km and 1.58 km. The mean absolute distance deviations obtained by ray tracing were approximately 12.4 and 23.5 times those obtained using the transmission-curve method for the 309-km and 659-km propagation distances， respectively. These results indicate that ray tracing is suitable for investigating the effects of the geomagnetic field， ray type， and three-dimensional electron-density structure on HF propagation paths， whereas the transmission-curve method combined with measured ionograms provides more stable estimates of ground distance for fixed point-to-point skywave links.
